Architect

Architect Financial Technologies Inc is a multinational derivatives exchange group and electronic brokerage designed for the AI economy.

Architect sells inference on Liquid Inference. A buyer names one of its models as architect/<model>, or names the model and pays the lowest offer that meets the buyer's rules.

Facts

Handle

architect

Website

https://architect.co/

On the exchange since

2026-09-16

Models

754

Offers

765

Regions

us

Precisions (declared)

provider-managed

Lowest price on

592 of 592 models

Reliability, last 3 days

Probes answered

85.47%

Hours with an answer

66.1%

Median response time

3.6s

Checked by the exchange

7 of 765 offers match the fingerprint of the model. 0 have a finished evaluation.

The exchange sends fixed prompts to each offer and compares the answers with a baseline for the model. It also runs benchmarks against the offers and keeps the results.

Data handling

• Zero retention, checked by the exchange
• No training, checked by the exchange

Models

• Abliterated Model: declared precision provider-managed, us, $1.000 input and $2.999 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
• Abliterated: Model Large: declared precision provider-managed, us, $2.999 input and $4.998 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
• Abliterated: Model Large Flash: declared precision provider-managed, us, $0.999 input and $1.997 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• Abliterated: Model Large V2: declared precision provider-managed, us, $2.997 input and $4.995 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
• Aion 2.0: declared precision provider-managed, us, $0.799 input and $1.598 output per million tokens, $0.200 cache read per million tokens, 131.1K tokens of context
• Aion 3.0: declared precision provider-managed, us, $2.995 input and $5.990 output per million tokens, $0.749 cache read per million tokens, 131.1K tokens of context
• Aion 3.0 Mini: declared precision provider-managed, us, $0.700 input and $1.400 output per million tokens, $0.180 cache read per million tokens, 131.1K tokens of context
• Aion 3.5: declared precision provider-managed, us, $3.002 input and $6.003 output per million tokens, $0.750 cache read per million tokens, 262.1K tokens of context
• Aion 3.5 Mini: declared precision provider-managed, us, $0.700 input and $1.400 output per million tokens, $0.180 cache read per million tokens, 262.1K tokens of context
• Aion: RP Llama 3.1 8B: declared precision provider-managed, us, $0.800 input and $1.600 output per million tokens, $0.800 cache read per million tokens, 32.8K tokens of context
• Alia 40B Instruct 2606: declared precision provider-managed, us, $0.300 input and $0.599 output per million tokens, $0.300 cache read per million tokens, 65.5K tokens of context
• Amoral: Gemma 3 27B V2: declared precision provider-managed, us, $0.301 input and $0.301 output per million tokens, $0.301 cache read per million tokens, 32.8K tokens of context
• Anthropic/voyage: Multilingual 2: declared precision provider-managed, us, $0.120 input per million tokens, 32K tokens of context
• Anubis 70B V1: declared precision provider-managed, us, $0.311 input and $0.311 output per million tokens, $0.311 cache read per million tokens, 65.5K tokens of context
• Anubis 70B V1.1: declared precision provider-managed, us, $0.311 input and $0.311 output per million tokens, $0.311 cache read per million tokens, 32.8K tokens of context
• Artemis V1.1: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Autoglm: Phone 9B Multilingual: declared precision provider-managed, us, $0.035 input and $0.138 output per million tokens, $0.035 cache read per million tokens, 65.5K tokens of context
• Base Conversationalai: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base Finance: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base General: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base Meeting: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base Phonecall: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base Video: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Base Voicemail: declared precision provider-managed, us, $0.00021 per second, 1 tokens of context
• Beam 1.0: declared precision provider-managed, us, $0.500 input and $1.501 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
• Beam 1.0 501B a23b: declared precision provider-managed, us, $0.401 input and $1.203 output per million tokens, $0.401 cache read per million tokens, 1M tokens of context
• Bielik 11B V3.0 Instruct: declared precision provider-managed, us, $0.479 input and $0.479 output per million tokens, $0.479 cache read per million tokens, 32.8K tokens of context
• Celeris 1: declared precision provider-managed, us, $2.003 input and $6.008 output per million tokens, $2.003 cache read per million tokens, 8,192 tokens of context
• Chat Latest: declared precision provider-managed, us, $5.008 input and $30.047 output per million tokens, $0.501 cache read per million tokens, 400K tokens of context
• Chirp: declared precision provider-managed, us, $0.000030 per character, 4,097 tokens of context
• Chroma: declared precision provider-managed, us, $0.025 per image, 32K tokens of context
• Claude 3.7 Sonnet Latest: declared precision provider-managed, us, $3.295 input and $16.473 output per million tokens, $0.329 cache read per million tokens, 200K tokens of context
• Claude 4 Opus: declared precision provider-managed, us, $16.471 input and $82.356 output per million tokens, $16.471 cache read per million tokens, 200K tokens of context
• Claude 4 Sonnet: declared precision provider-managed, us, $3.292 input and $16.461 output per million tokens, $3.292 cache read per million tokens, 200K tokens of context
• Claude: Fable 5: declared precision provider-managed, us, $10.009 input and $50.047 output per million tokens, $1.001 cache read per million tokens, 1M tokens of context
• Claude: Fable 5 1: declared precision provider-managed, us, $9.995 input and $49.976 output per million tokens, $0.250 cache read per million tokens, 1M tokens of context
• Claude: Fable Latest: declared precision provider-managed, us, $10.024 input and $50.122 output per million tokens, $0.251 cache read per million tokens, 1M tokens of context
• Claude: Haiku 4 5: declared precision provider-managed, us, $1.002 input and $5.008 output per million tokens, $0.100 cache read, $1.252 cache write, $2.003 one-hour cache write per million tokens, 200K tokens of context
• Claude: Haiku 4 5:thinking: declared precision provider-managed, us, $0.999 input and $4.994 output per million tokens, $0.100 cache read per million tokens, 200K tokens of context
• Claude: Haiku 5 5: declared precision provider-managed, us, $0.100 input and $0.501 output per million tokens, $0.010 cache read per million tokens, 100K tokens of context
• Claude: Haiku Latest: declared precision provider-managed, us, $0.100 input and $0.499 output per million tokens, $0.0100 cache read per million tokens, 100K tokens of context
• Claude: Opus 4 1: declared precision provider-managed, us, $15.036 input and $75.182 output per million tokens, $1.504 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 1:thinking: declared precision provider-managed, us, $14.969 input and $74.843 output per million tokens, $1.497 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 1:thinking:1024: declared precision provider-managed, us, $15.011 input and $75.057 output per million tokens, $1.501 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 1:thinking:32768: declared precision provider-managed, us, $14.982 input and $74.911 output per million tokens, $1.498 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 1:thinking:8192: declared precision provider-managed, us, $14.972 input and $74.859 output per million tokens, $1.497 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 5: declared precision provider-managed, us, $5.011 input and $25.055 output per million tokens, $0.501 cache read, $6.264 cache write, $10.022 one-hour cache write per million tokens, 200K tokens of context
• Claude: Opus 4 5:thinking: declared precision provider-managed, us, $5.006 input and $25.028 output per million tokens, $0.501 cache read per million tokens, 200K tokens of context
• Claude: Opus 4 6: declared precision provider-managed, us, $4.992 input and $24.959 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 6:thinking: declared precision provider-managed, us, $5.000 input and $25.002 output per million tokens, $0.500 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 6:thinking:low: declared precision provider-managed, us, $5.006 input and $25.032 output per million tokens, $0.501 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 6:thinking:max: declared precision provider-managed, us, $5.010 input and $25.051 output per million tokens, $0.501 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 6:thinking:medium: declared precision provider-managed, us, $4.994 input and $24.968 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 7: declared precision provider-managed, us, $4.994 input and $24.968 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 7:thinking: declared precision provider-managed, us, $5.000 input and $24.999 output per million tokens, $0.500 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 8: declared precision provider-managed, us, $4.992 input and $24.961 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Claude: Opus 4 8:thinking: declared precision provider-managed, us, $4.989 input and $24.945 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Claude: Opus 5: declared precision provider-managed, us, $4.996 input and $24.980 output per million tokens, $0.500 cache read per million tokens, 1M tokens of context
• Claude: Opus 5 5: declared precision provider-managed, us, $3.992 input and $19.959 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claude: Opus Latest: declared precision provider-managed, us, $4.000 input and $19.998 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 4 5: declared precision provider-managed, us, $3.003 input and $15.017 output per million tokens, $0.300 cache read per million tokens, 200K tokens of context
• Claude: Sonnet 4 5:thinking: declared precision provider-managed, us, $3.006 input and $15.030 output per million tokens, $0.301 cache read per million tokens, 200K tokens of context
• Claude: Sonnet 4 6: declared precision provider-managed, us, $2.999 input and $14.995 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 4 6:thinking: declared precision provider-managed, us, $3.001 input and $15.004 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 5: declared precision provider-managed, us, $2.002 input and $10.011 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 5 5: declared precision provider-managed, us, $1.999 input and $9.993 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 5 5:thinking: declared precision provider-managed, us, $1.998 input and $9.988 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• Claude: Sonnet 5:thinking: declared precision provider-managed, us, $1.996 input and $9.980 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claude: Sonnet Latest: declared precision provider-managed, us, $1.998 input and $9.990 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• Claw High: declared precision provider-managed, us, $0.599 input and $1.099 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claw Low: declared precision provider-managed, us, $0.600 input and $1.100 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Claw Medium: declared precision provider-managed, us, $0.599 input and $1.099 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Codestral 2405: declared precision provider-managed, us, $1.002 input and $3.007 output per million tokens, $1.002 cache read per million tokens, 32K tokens of context
• Codestral 2508: declared precision provider-managed, us, $0.300 input and $0.899 output per million tokens, $0.300 cache read per million tokens, 256K tokens of context
• Coding Router: declared precision provider-managed, us, $1.100 input and $2.199 output per million tokens, $0.110 cache read per million tokens, 1M tokens of context
• Coding Router:high: declared precision provider-managed, us, $1.101 input and $2.202 output per million tokens, $0.110 cache read per million tokens, 1M tokens of context
• Coding Router:low: declared precision provider-managed, us, $0.140 input and $0.280 output per million tokens, $0.028 cache read per million tokens, 1M tokens of context
• Coding Router:max: declared precision provider-managed, us, $4.995 input and $29.968 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• Coding Router:medium: declared precision provider-managed, us, $0.140 input and $0.279 output per million tokens, $0.028 cache read per million tokens, 1M tokens of context
• Cogito V1 Preview Qwen 32B: declared precision provider-managed, us, $1.801 input and $1.801 output per million tokens, $1.801 cache read per million tokens, 128K tokens of context
• Command A Reasoning 08 2025: declared precision provider-managed, us, $2.500 input and $9.999 output per million tokens, $2.500 cache read per million tokens, 256K tokens of context
• Command R Plus 08 2024: declared precision provider-managed, us, $2.858 input and $14.253 output per million tokens, $2.858 cache read per million tokens, 128K tokens of context
• Cyberheabsy: declared precision provider-managed, us, $1.499 input and $4.498 output per million tokens, $0.275 cache read per million tokens, 1M tokens of context
• Cydonia 24B V2: declared precision provider-managed, us, $0.100 input and $0.121 output per million tokens, $0.100 cache read per million tokens, 32.8K tokens of context
• Cydonia 24B V4: declared precision provider-managed, us, $0.201 input and $0.242 output per million tokens, $0.201 cache read per million tokens, 32.8K tokens of context
• Cydonia 24B V4.1: declared precision provider-managed, us, $0.300 input and $0.500 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context
• Cydonia 24B V4.3: declared precision provider-managed, us, $0.120 input and $0.150 output per million tokens, $0.120 cache read per million tokens, 65.5K tokens of context
• DeepSeek Chat: declared precision provider-managed, us, $0.150 input and $0.600 output per million tokens, $0.0030 cache read per million tokens, 131.1K tokens of context
• DeepSeek Latest: declared precision provider-managed, us, $0.660 input and $1.979 output per million tokens, $0.022 cache read per million tokens, 1M tokens of context
• DeepSeek R1: declared precision provider-managed, us, $0.698 input and $2.395 output per million tokens, $0.698 cache read per million tokens, 163.8K tokens of context
• DeepSeek R1 0528: declared precision provider-managed, us, $0.499 input and $2.146 output per million tokens, $0.499 cache read per million tokens, 163.8K tokens of context
• DeepSeek R1 0528 Turbo: declared precision provider-managed, us, $0.999 input and $2.997 output per million tokens, $0.999 cache read per million tokens, 32.8K tokens of context
• DeepSeek R1 Distill Llama 70B Abliterated: declared precision provider-managed, us, $0.701 input and $0.701 output per million tokens, $0.701 cache read per million tokens, 16.4K tokens of context
• DeepSeek R1 Distill Qwen 32B: declared precision provider-managed, us, $0.270 input and $0.270 output per million tokens, $0.270 cache read per million tokens, 131.1K tokens of context
• DeepSeek R1 Distill Qwen 32B Abliterated: declared precision provider-managed, us, $1.397 input and $1.397 output per million tokens, $1.397 cache read per million tokens, 16.4K tokens of context
• DeepSeek R1 Turbo: declared precision provider-managed, us, $1.001 input and $3.002 output per million tokens, $1.001 cache read per million tokens, 41K tokens of context
• DeepSeek Reasoner: declared precision provider-managed, us, $0.150 input and $0.600 output per million tokens, $0.0030 cache read per million tokens, 131.1K tokens of context
• DeepSeek V3: declared precision provider-managed, us, $0.320 input and $0.891 output per million tokens, $0.320 cache read per million tokens, 163.8K tokens of context
• DeepSeek V3 0324: declared precision provider-managed, us, $0.200 input and $0.770 output per million tokens, $0.135 cache read per million tokens, 128K tokens of context
• DeepSeek V3.1: declared precision provider-managed, us, $0.200 input and $0.700 output per million tokens, $0.200 cache read per million tokens, 128K tokens of context
• DeepSeek V3.1 Terminus: declared precision provider-managed, us, $0.250 input and $0.701 output per million tokens, $0.250 cache read per million tokens, 128K tokens of context
• DeepSeek V3.1 Terminus:thinking: declared precision provider-managed, us, $0.250 input and $0.699 output per million tokens, $0.250 cache read per million tokens, 128K tokens of context
• DeepSeek v3.1:thinking: declared precision provider-managed, us, $0.200 input and $0.701 output per million tokens, $0.200 cache read per million tokens, 128K tokens of context
• DeepSeek V3.2 Exp: declared precision provider-managed, us, $0.280 input and $0.419 output per million tokens, $0.280 cache read per million tokens, 163.8K tokens of context
• DeepSeek V3.2 Exp Thinking: declared precision provider-managed, us, $0.280 input and $0.420 output per million tokens, $0.280 cache read per million tokens, 163.8K tokens of context
• DeepSeek v3.2:thinking: declared precision provider-managed, us, $0.208 input and $0.309 output per million tokens, $0.022 cache read per million tokens, 163K tokens of context
• DeepSeek V4 Flash 0423: declared precision provider-managed, us, $0.140 input and $0.280 output per million tokens, $0.028 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Flash 0423:thinking: declared precision provider-managed, us, $0.140 input and $0.280 output per million tokens, $0.028 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Flash Latest: declared precision provider-managed, us, $0.100 input and $0.599 output per million tokens, $0.0042 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Flash Vision Exp: declared precision provider-managed, us, $0.216 input and $0.647 output per million tokens, $0.0069 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Flash:thinking: declared precision provider-managed, us, $0.140 input and $0.280 output per million tokens, $0.0028 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Pro 0813:thinking: declared precision provider-managed, us, $0.660 input and $1.979 output per million tokens, $0.022 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Pro:thinking: declared precision provider-managed, us, $0.701 input and $1.402 output per million tokens, $0.070 cache read per million tokens, 1M tokens of context
• DeepSeek V4.1 Flash 1017 Heretic: declared precision provider-managed, us, $0.198 input and $0.793 output per million tokens, $0.013 cache read per million tokens, 512K tokens of context
• DeepSeek V4.1 Flash 1017 Heretic:thinking: declared precision provider-managed, us, $0.198 input and $0.791 output per million tokens, $0.013 cache read per million tokens, 512K tokens of context
• DeepSeek: Chat Cheaper: declared precision provider-managed, us, $0.200 input and $0.769 output per million tokens, $0.135 cache read per million tokens, 128K tokens of context
• Devstral 2 123B Instruct 2512: declared precision provider-managed, us, $0.400 input and $1.400 output per million tokens, $0.400 cache read per million tokens, 262.1K tokens of context
• Devstral: Small 2505: declared precision provider-managed, us, $0.060 input and $0.060 output per million tokens, $0.060 cache read per million tokens, 32.8K tokens of context
• Devstral: Small Latest: declared precision provider-managed, us, $0.100 input and $0.300 output per million tokens, $0.100 cache read per million tokens, 256K tokens of context
• Diffusiongemma: declared precision provider-managed, us, $0.050 input and $0.150 output per million tokens, $0.025 cache read per million tokens, 262.1K tokens of context
• Doubao: Seed 2.0 Code Preview 260215: declared precision provider-managed, us, $0.784 input and $3.902 output per million tokens, $0.784 cache read per million tokens, 128K tokens of context
• Doubao: Seed 2.0 Lite 260215: declared precision provider-managed, us, $0.250 input and $2.001 output per million tokens, $0.250 cache read per million tokens, 128K tokens of context
• Doubao: Seed 2.0 Mini 260215: declared precision provider-managed, us, $0.100 input and $0.483 output per million tokens, $0.100 cache read per million tokens, 128K tokens of context
• Doubao: Seed 2.0 Pro 260215: declared precision provider-managed, us, $0.782 input and $3.875 output per million tokens, $0.782 cache read per million tokens, 256K tokens of context
• Doubao: Seed Character: declared precision provider-managed, us, $0.150 input and $0.370 output per million tokens, $0.030 cache read per million tokens, 32K tokens of context
• Dracarys 72B Instruct: declared precision provider-managed, us, $0.492 input and $0.492 output per million tokens, $0.492 cache read per million tokens, 32.8K tokens of context
• Dreamshaper Xl: declared precision provider-managed, us, $0.0051 per image, 32K tokens of context
• eleven_flash_v2: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• eleven_flash_v2_5: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• eleven_multilingual_v2: declared precision provider-managed, us, $0.000080 per character, 4,097 tokens of context
• eleven_turbo_v2: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• eleven_turbo_v2_5: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• eleven_v3: declared precision provider-managed, us, $0.000080 per character, 4,097 tokens of context
• eleven_v3_conversational: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• eleven_v4: declared precision provider-managed, us, $0.000080 per character, 4,097 tokens of context
• eleven_v4_turbo: declared precision provider-managed, us, $0.000040 per character, 4,097 tokens of context
• Ember 1: declared precision provider-managed, us, $3.006 input and $15.031 output per million tokens, $0.301 cache read per million tokens, 1M tokens of context
• Enhanced: declared precision provider-managed, us, $0.00024 per second, 1 tokens of context
• Enhanced Finance: declared precision provider-managed, us, $0.00024 per second, 1 tokens of context
• Enhanced General: declared precision provider-managed, us, $0.00024 per second, 1 tokens of context
• Enhanced Meeting: declared precision provider-managed, us, $0.00024 per second, 1 tokens of context
• Enhanced Phonecall: declared precision provider-managed, us, $0.00024 per second, 1 tokens of context
• Eva: Llama 3.33 70B V0.0: declared precision provider-managed, us, $2.003 input and $2.003 output per million tokens, $2.003 cache read per million tokens, 32.8K tokens of context
• Eva: Llama 3.33 70B V0.1: declared precision provider-managed, us, $2.002 input and $2.002 output per million tokens, $2.002 cache read per million tokens, 32.8K tokens of context
• Eva: Qwen 2.5 32B V0.2: declared precision provider-managed, us, $0.799 input and $0.799 output per million tokens, $0.799 cache read per million tokens, 16.4K tokens of context
• Eva: Qwen 2.5 72B V0.2: declared precision provider-managed, us, $0.799 input and $0.799 output per million tokens, $0.799 cache read per million tokens, 16.4K tokens of context
• Fast Sdxl: declared precision provider-managed, us, $0.0051 per image, 32K tokens of context
• Fluently Xl: declared precision provider-managed, us, $0.0051 per image, 32K tokens of context
• Flux 2 Dev: declared precision provider-managed, us, $0.020 per image, 32K tokens of context
• Flux 2 Klein Base 4B: declared precision provider-managed, us, $0.010 per image, 32K tokens of context
• Flux 2 Klein Base 9B: declared precision provider-managed, us, $0.015 per image, 32K tokens of context
• Flux 2 Pro: declared precision provider-managed, us, $0.051 per image, 32K tokens of context
• Flux Dev: declared precision provider-managed, us, $0.025 per image, 32K tokens of context
• Flux: Kontext Max: declared precision provider-managed, us, $0.080 per image, 32K tokens of context
• Flux: Kontext Pro: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Flux: Pro 1.1: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Flux: Pro 1.1 Ultra: declared precision provider-managed, us, $0.060 per image, 32K tokens of context
• Flux: Pro V1.1: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Flux: Pro V1.1 Ultra: declared precision provider-managed, us, $0.060 per image, 32K tokens of context
• Fugu Max: declared precision provider-managed, us, $2.000 input and $6.001 output per million tokens, $0.250 cache read per million tokens, 1M tokens of context
• Fugu Ultra: declared precision provider-managed, us, $5.002 input and $30.009 output per million tokens, $0.500 cache read per million tokens, 272K tokens of context
• Fugu: Ultra V1.1: declared precision provider-managed, us, $5.002 input and $30.012 output per million tokens, $0.500 cache read per million tokens, 272K tokens of context
• Gemini 2.0 Pro Exp 02 05: declared precision provider-managed, us, $1.990 input and $10.005 output per million tokens, $0.497 cache read per million tokens, 200K tokens of context
• Gemini 2.0 Pro Reasoner: declared precision provider-managed, us, $1.290 input and $9.988 output per million tokens, $0.323 cache read per million tokens, 128K tokens of context
• Gemini 2.5 Flash: declared precision provider-managed, us, $0.299 input and $2.495 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Image: declared precision provider-managed, us, $0.300 input and $30.004 output per million tokens, $0.030 cache read, $0.083 cache write per million tokens, 32.8K tokens of context
• Gemini 2.5 Flash Lite: declared precision provider-managed, us, $0.100 input and $0.399 output per million tokens, $0.0100 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Lite Preview 06 17: declared precision provider-managed, us, $0.150 input and $0.601 output per million tokens, $0.015 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Lite Preview 09 2025: declared precision provider-managed, us, $0.100 input and $0.401 output per million tokens, $0.010 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Lite Preview 09 2025 Thinking: declared precision provider-managed, us, $0.150 input and $0.599 output per million tokens, $0.015 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Nothinking: declared precision provider-managed, us, $0.299 input and $2.495 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 04 17: declared precision provider-managed, us, $0.299 input and $2.495 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 04 17:thinking: declared precision provider-managed, us, $0.300 input and $3.495 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 05 20: declared precision provider-managed, us, $0.300 input and $2.499 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 05 20:thinking: declared precision provider-managed, us, $0.300 input and $3.498 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 09 2025: declared precision provider-managed, us, $0.300 input and $2.498 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Flash Preview 09 2025 Thinking: declared precision provider-managed, us, $0.301 input and $2.505 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Pro: declared precision provider-managed, us, $1.248 input and $9.981 output per million tokens, $0.125 cache read per million tokens, 200K tokens of context
• Gemini 2.5 Pro Exp 03 25: declared precision provider-managed, us, $2.500 input and $10.000 output per million tokens, $0.250 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Pro Preview 03 25: declared precision provider-managed, us, $2.504 input and $10.014 output per million tokens, $0.250 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Pro Preview 05 06: declared precision provider-managed, us, $2.494 input and $9.977 output per million tokens, $0.249 cache read per million tokens, 1M tokens of context
• Gemini 2.5 Pro Preview 06 05: declared precision provider-managed, us, $2.504 input and $10.018 output per million tokens, $0.250 cache read per million tokens, 200K tokens of context
• Gemini 3 Flash Preview: declared precision provider-managed, us, $0.500 input and $3.001 output per million tokens, $0.050 cache read, $0.083 cache write per million tokens, 1M tokens of context
• Gemini 3 Flash Preview Thinking: declared precision provider-managed, us, $0.499 input and $2.994 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
• Gemini 3 Pro Image Preview: declared precision provider-managed, us, $2.003 input and $120.186 output per million tokens, $0.200 cache read, $0.376 cache write per million tokens, 65.5K tokens of context
• Gemini 3.1 Flash Image Preview: declared precision provider-managed, us, $0.500 input and $59.976 output per million tokens, $0.500 cache read per million tokens, 65.5K tokens of context
• Gemini 3.1 Flash Lite: declared precision provider-managed, us, $0.250 input and $1.498 output per million tokens, $0.025 cache read, $0.083 cache write per million tokens, 1M tokens of context
• Gemini 3.1 Flash Lite Preview: declared precision provider-managed, us, $0.250 input and $1.501 output per million tokens, $0.025 cache read, $0.083 cache write per million tokens, 1M tokens of context
• Gemini 3.1 Pro Preview: declared precision provider-managed, us, $2.004 input and $12.024 output per million tokens, $0.200 cache read, $0.376 cache write per million tokens, 200K tokens of context
• Gemini 3.1 Pro Preview Customtools: declared precision provider-managed, us, $1.997 input and $11.981 output per million tokens, $0.200 cache read, $0.374 cache write per million tokens, 200K tokens of context
• Gemini 3.1 Pro Preview High: declared precision provider-managed, us, $2.002 input and $12.009 output per million tokens, $0.200 cache read per million tokens, 200K tokens of context
• Gemini 3.1 Pro Preview Low: declared precision provider-managed, us, $2.001 input and $12.004 output per million tokens, $0.200 cache read per million tokens, 200K tokens of context
• Gemini 3.5 Flash: declared precision provider-managed, us, $1.497 input and $8.979 output per million tokens, $0.150 cache read, $0.083 cache write per million tokens, 1M tokens of context
• Gemini 3.5 Flash Lite: declared precision provider-managed, us, $0.300 input and $2.497 output per million tokens, $0.030 cache read, $0.083 cache write per million tokens, 1M tokens of context
• Gemini 3.5 Flash Thinking: declared precision provider-managed, us, $1.499 input and $8.993 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
• Gemini 3.6 Flash: declared precision provider-managed, us, $0.749 input and $3.743 output per million tokens, $0.075 cache read, $0.042 cache write per million tokens, 1M tokens of context
• Gemini 3.7 Flash: declared precision provider-managed, us, $0.750 input and $3.750 output per million tokens, $0.075 cache read, $0.042 cache write per million tokens, 1M tokens of context
• Gemini 3.8 Flash: declared precision provider-managed, us, $0.748 input and $3.742 output per million tokens, $0.075 cache read, $0.042 cache write per million tokens, 1M tokens of context
• Gemini: Embedding 001: declared precision provider-managed, us, $0.150 input per million tokens, 8,192 tokens of context
• Gemini: Embedding 2 Preview: declared precision provider-managed, us, $0.200 input per million tokens, 8,192 tokens of context
• Gemini: Exp 1206: declared precision provider-managed, us, $1.258 input and $10.000 output per million tokens, $0.629 cache read per million tokens, 200K tokens of context
• Gemini: Flash Latest: declared precision provider-managed, us, $0.751 input and $3.757 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
• Gemini: Flash Lite Latest: declared precision provider-managed, us, $0.300 input and $2.501 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Gemini: Pro Latest: declared precision provider-managed, us, $1.997 input and $11.982 output per million tokens, $0.200 cache read per million tokens, 200K tokens of context
• Gemma 3 12B It: declared precision provider-managed, us, $0.271 input and $0.271 output per million tokens, $0.271 cache read per million tokens, 131.1K tokens of context
• Gemma 3 4B It: declared precision provider-managed, us, $0.201 input and $0.201 output per million tokens, $0.201 cache read per million tokens, 128K tokens of context
• Gemma 4 12B It: declared precision provider-managed, us, $0.050 input and $0.250 output per million tokens, $0.025 cache read per million tokens, 131.1K tokens of context
• Gemma 4 12B It Semancer: declared precision provider-managed, us, $0.050 input and $0.249 output per million tokens, $0.025 cache read per million tokens, 131.1K tokens of context
• Gemma 4 12B It Starry Ocean: declared precision provider-managed, us, $0.050 input and $0.250 output per million tokens, $0.025 cache read per million tokens, 131.1K tokens of context
• Gemma 4 12B It Station Keeper: declared precision provider-managed, us, $0.050 input and $0.250 output per million tokens, $0.025 cache read per million tokens, 131.1K tokens of context
• Gemma 4 26B a4b It Chimerax: declared precision provider-managed, us, $0.120 input and $0.380 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Chimeraxheretic: declared precision provider-managed, us, $0.120 input and $0.379 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Cybersecurity: declared precision provider-managed, us, $0.106 input and $0.335 output per million tokens, $0.053 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Darksoul: declared precision provider-managed, us, $0.120 input and $0.381 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Luminous: declared precision provider-managed, us, $0.120 input and $0.379 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Moonlight: declared precision provider-managed, us, $0.120 input and $0.381 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Musica: declared precision provider-managed, us, $0.120 input and $0.379 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Opusdistill: declared precision provider-managed, us, $0.120 input and $0.381 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It Shadowsiren: declared precision provider-managed, us, $0.120 input and $0.380 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b It:thinking: declared precision provider-managed, us, $0.032 input and $0.097 output per million tokens, $0.016 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b Meromero: declared precision provider-managed, us, $0.120 input and $0.380 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 26B a4b Meromero:thinking: declared precision provider-managed, us, $0.120 input and $0.380 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Agares V1: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Animus V14.1: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Assguard: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Claude 4.6 Opus Reasoning Distilled: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.031 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Cognitive Unshackled: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Dark Gemistry: declared precision provider-managed, us, $0.307 input and $0.307 output per million tokens, $0.307 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Darkidol: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Fabled: declared precision provider-managed, us, $0.305 input and $0.305 output per million tokens, $0.305 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Garnetv 2: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Gembrain Uncensored Heretic: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Gembrain X Core: declared precision provider-managed, us, $0.307 input and $0.307 output per million tokens, $0.307 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Isometry RP: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Darkidol: declared precision provider-managed, us, $0.100 input and $0.450 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Fabled: declared precision provider-managed, us, $0.100 input and $0.450 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Garnet: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Gembrain: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Gemsicle: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Isometry: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Novelist: declared precision provider-managed, us, $0.100 input and $0.450 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It Scarlet: declared precision provider-managed, us, $0.100 input and $0.450 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B It:thinking: declared precision provider-managed, us, $0.100 input and $0.341 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B K1 V5: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Meromero: declared precision provider-managed, us, $0.307 input and $0.307 output per million tokens, $0.307 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Meromero V2: declared precision provider-managed, us, $0.100 input and $0.449 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Meromero v2:thinking: declared precision provider-managed, us, $0.100 input and $0.450 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Novelist: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Queen: declared precision provider-managed, us, $0.305 input and $0.305 output per million tokens, $0.305 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Sdft Heretic RP: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma 4 31B Styletune: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Gemma: Sea Lion V4 27B It: declared precision provider-managed, us, $0.200 input and $0.399 output per million tokens, $0.200 cache read per million tokens, 131.1K tokens of context
• Generative: declared precision provider-managed, us, $0.000030 per character, 4,097 tokens of context
• Glimpse: declared precision provider-managed, us, $0.629 input and $3.143 output per million tokens, $0.063 cache read per million tokens, 262.1K tokens of context
• GLM 4.5: declared precision provider-managed, us, $0.300 input and $1.302 output per million tokens, $0.300 cache read per million tokens, 128K tokens of context
• GLM 4.5 Air: declared precision provider-managed, us, $0.130 input and $0.850 output per million tokens, $0.130 cache read per million tokens, 131.1K tokens of context
• GLM 4.5 Air:thinking: declared precision provider-managed, us, $0.130 input and $0.848 output per million tokens, $0.025 cache read per million tokens, 128K tokens of context
• GLM 4.5:thinking: declared precision provider-managed, us, $0.299 input and $1.297 output per million tokens, $0.299 cache read per million tokens, 128K tokens of context
• GLM 4.5v: declared precision provider-managed, us, $0.601 input and $1.804 output per million tokens, $0.601 cache read per million tokens, 65.5K tokens of context
• GLM 4.5v:thinking: declared precision provider-managed, us, $0.599 input and $1.796 output per million tokens, $0.599 cache read per million tokens, 65.5K tokens of context
• GLM 4.6: declared precision provider-managed, us, $0.499 input and $1.997 output per million tokens, $0.499 cache read per million tokens, 202.8K tokens of context
• GLM 4.6 Derestricted V5: declared precision provider-managed, us, $0.399 input and $1.497 output per million tokens, $0.399 cache read per million tokens, 131.1K tokens of context
• GLM 4.6 Original: declared precision provider-managed, us, $0.550 input and $2.199 output per million tokens, $0.110 cache read per million tokens, 256K tokens of context
• GLM 4.6 Turbo: declared precision provider-managed, us, $0.551 input and $2.203 output per million tokens, $0.110 cache read per million tokens, 204.8K tokens of context
• GLM 4.6 Turbo:thinking: declared precision provider-managed, us, $0.549 input and $2.195 output per million tokens, $0.110 cache read per million tokens, 204.8K tokens of context
• GLM 4.6:thinking: declared precision provider-managed, us, $0.549 input and $2.198 output per million tokens, $0.110 cache read per million tokens, 200K tokens of context
• GLM 4.6v: declared precision provider-managed, us, $0.299 input and $0.898 output per million tokens, $0.299 cache read per million tokens, 128K tokens of context
• GLM 4.6v Flash: declared precision provider-managed, us, $0.300 input and $0.901 output per million tokens, $0.300 cache read per million tokens, 131.1K tokens of context
• GLM 4.6v Original: declared precision provider-managed, us, $0.600 input and $0.901 output per million tokens, $0.600 cache read per million tokens, 128K tokens of context
• GLM 4.7 Flash:thinking: declared precision provider-managed, us, $0.070 input and $0.400 output per million tokens, $0.0100 cache read per million tokens, 200K tokens of context
• GLM 4.7 Original: declared precision provider-managed, us, $0.401 input and $1.933 output per million tokens, $0.080 cache read per million tokens, 200K tokens of context
• GLM 4.7 Original:thinking: declared precision provider-managed, us, $0.401 input and $1.934 output per million tokens, $0.080 cache read per million tokens, 200K tokens of context
• GLM 4.7:thinking: declared precision provider-managed, us, $0.400 input and $1.926 output per million tokens, $0.080 cache read per million tokens, 200K tokens of context
• GLM 5: declared precision provider-managed, us, $0.601 input and $1.902 output per million tokens, $0.100 cache read per million tokens, 200K tokens of context
• GLM 5 Original: declared precision provider-managed, us, $0.599 input and $1.898 output per million tokens, $0.100 cache read per million tokens, 200K tokens of context
• GLM 5 Original:thinking: declared precision provider-managed, us, $0.599 input and $1.898 output per million tokens, $0.100 cache read per million tokens, 200K tokens of context
• GLM 5 Turbo: declared precision provider-managed, us, $1.199 input and $3.995 output per million tokens, $0.240 cache read per million tokens, 202.8K tokens of context
• GLM 5:thinking: declared precision provider-managed, us, $0.599 input and $1.897 output per million tokens, $0.100 cache read per million tokens, 200K tokens of context
• GLM 5.1:thinking: declared precision provider-managed, us, $0.701 input and $2.502 output per million tokens, $0.180 cache read per million tokens, 200K tokens of context
• GLM 5.2:thinking: declared precision provider-managed, us, $0.420 input and $1.319 output per million tokens, $0.078 cache read per million tokens, 1M tokens of context
• GLM 5.3 Flash Apex: declared precision provider-managed, us, $0.150 input and $0.501 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
• GLM 5.3 Flash Apex Abliterated: declared precision provider-managed, us, $0.150 input and $0.500 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
• GLM 5.3 Flash Cybersecurity: declared precision provider-managed, us, $0.150 input and $0.501 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
• GLM 5.3 Flashx: declared precision provider-managed, us, $0.369 input and $1.247 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
• GLM 5.3 Uncensored: declared precision provider-managed, us, $1.249 input and $2.249 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
• GLM 5.3:thinking: declared precision provider-managed, us, $0.599 input and $1.099 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• GLM 5v Turbo: declared precision provider-managed, us, $1.199 input and $3.996 output per million tokens, $0.240 cache read per million tokens, 202.8K tokens of context
• GLM 5v Turbo:thinking: declared precision provider-managed, us, $1.197 input and $3.991 output per million tokens, $0.239 cache read per million tokens, 202.8K tokens of context
• GLM Image: declared precision provider-managed, us, $0.120 per image, 32K tokens of context
• GLM Latest: declared precision provider-managed, us, $0.599 input and $1.098 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• GPT 3.5 Turbo: declared precision provider-managed, us, $0.500 input and $1.500 output per million tokens, $0.500 cache read per million tokens, 4,097 tokens of context
• GPT 4.1: declared precision provider-managed, us, $2.004 input and $8.018 output per million tokens, $0.501 cache read per million tokens, 1M tokens of context
• GPT 4.1 2025 04 14: declared precision provider-managed, us, $1.998 input and $7.990 output per million tokens, $0.499 cache read per million tokens, 1M tokens of context
• GPT 4.1 Mini: declared precision provider-managed, us, $0.400 input and $1.602 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• GPT 4.1 Mini 2025 04 14: declared precision provider-managed, us, $0.400 input and $1.601 output per million tokens, $0.100 cache read per million tokens, 1M tokens of context
• GPT 4.1 Nano: declared precision provider-managed, us, $0.100 input and $0.401 output per million tokens, $0.025 cache read per million tokens, 1M tokens of context
• GPT 4o: declared precision provider-managed, us, $2.496 input and $9.985 output per million tokens, $1.248 cache read per million tokens, 128K tokens of context
• GPT 4o 2024 08 06: declared precision provider-managed, us, $2.503 input and $10.010 output per million tokens, $1.251 cache read per million tokens, 128K tokens of context
• GPT 4o 2024 11 20: declared precision provider-managed, us, $2.505 input and $10.019 output per million tokens, $1.252 cache read per million tokens, 128K tokens of context
• GPT 4o Mini: declared precision provider-managed, us, $0.150 input and $0.600 output per million tokens, $0.075 cache read per million tokens, 128K tokens of context
• GPT 5: declared precision provider-managed, us, $1.251 input and $10.011 output per million tokens, $0.125 cache read per million tokens, 400K tokens of context
• GPT 5 2025 08 07: declared precision provider-managed, us, $1.248 input and $9.984 output per million tokens, $0.125 cache read per million tokens, 400K tokens of context
• GPT 5 Codex: declared precision provider-managed, us, $1.247 input and $9.980 output per million tokens, $0.125 cache read per million tokens, 272K tokens of context
• GPT 5 Mini: declared precision provider-managed, us, $0.250 input and $1.998 output per million tokens, $0.025 cache read per million tokens, 400K tokens of context
• GPT 5 Mini 2025 08 07: declared precision provider-managed, us, $0.249 input and $1.995 output per million tokens, $0.025 cache read per million tokens, 400K tokens of context
• GPT 5 Nano: declared precision provider-managed, us, $0.050 input and $0.400 output per million tokens, $0.0050 cache read per million tokens, 400K tokens of context
• GPT 5 Nano 2025 08 07: declared precision provider-managed, us, $0.050 input and $0.399 output per million tokens, $0.0050 cache read per million tokens, 400K tokens of context
• GPT 5 Pro: declared precision provider-managed, us, $15.002 input and $120.015 output per million tokens, $1.500 cache read per million tokens, 400K tokens of context
• GPT 5.1: declared precision provider-managed, us, $1.248 input and $9.982 output per million tokens, $0.125 cache read per million tokens, 400K tokens of context
• GPT 5.1 2025 11 13: declared precision provider-managed, us, $1.252 input and $10.017 output per million tokens, $0.125 cache read per million tokens, 400K tokens of context
• GPT 5.1 Codex: declared precision provider-managed, us, $1.251 input and $10.012 output per million tokens, $0.125 cache read per million tokens, 272K tokens of context
• GPT 5.1 Codex Max: declared precision provider-managed, us, $1.247 input and $9.978 output per million tokens, $0.125 cache read per million tokens, 272K tokens of context
• GPT 5.1 Codex Mini: declared precision provider-managed, us, $0.250 input and $2.001 output per million tokens, $0.025 cache read per million tokens, 272K tokens of context
• GPT 5.2 2025 12 11: declared precision provider-managed, us, $1.753 input and $14.025 output per million tokens, $0.175 cache read per million tokens, 400K tokens of context
• GPT 5.2 Codex: declared precision provider-managed, us, $1.753 input and $14.027 output per million tokens, $0.175 cache read per million tokens, 272K tokens of context
• GPT 5.2 Pro 2025 12 11: declared precision provider-managed, us, $21.018 input and $168.141 output per million tokens, $21.018 cache read per million tokens, 400K tokens of context
• GPT 5.4 2026 03 05: declared precision provider-managed, us, $2.500 input and $14.998 output per million tokens, $0.250 cache read per million tokens, 272K tokens of context
• GPT 5.4 Mini 2026 03 17: declared precision provider-managed, us, $0.749 input and $4.495 output per million tokens, $0.075 cache read per million tokens, 400K tokens of context
• GPT 5.4 Nano: declared precision provider-managed, us, $0.200 input and $1.250 output per million tokens, $0.020 cache read per million tokens, 400K tokens of context
• GPT 5.4 Nano 2026 03 17: declared precision provider-managed, us, $0.200 input and $1.249 output per million tokens, $0.020 cache read per million tokens, 400K tokens of context
• GPT 5.4 Pro 2026 03 05: declared precision provider-managed, us, $29.973 input and $179.838 output per million tokens, $29.973 cache read per million tokens, 272K tokens of context
• GPT 5.5 2026 04 23: declared precision provider-managed, us, $5.007 input and $30.040 output per million tokens, $0.501 cache read per million tokens, 272K tokens of context
• GPT 5.5 Pro 2026 04 23: declared precision provider-managed, us, $29.984 input and $179.901 output per million tokens, $29.984 cache read per million tokens, 272K tokens of context
• GPT 6 Astra Pro: declared precision provider-managed, us, $9.991 input and $49.953 output per million tokens, $0.999 cache read per million tokens, 272K tokens of context
• GPT 6 Luna Pro: declared precision provider-managed, us, $0.100 input and $0.500 output per million tokens, $0.010 cache read per million tokens, 272K tokens of context
• GPT 6 Sol Pro: declared precision provider-managed, us, $1.995 input and $9.976 output per million tokens, $0.200 cache read per million tokens, 272K tokens of context
• GPT 6.1 Sol Pro: declared precision provider-managed, us, $2.001 input and $10.005 output per million tokens, $0.100 cache read per million tokens, 272K tokens of context
• GPT 6.1 Terra: declared precision provider-managed, us, $1.002 input and $5.009 output per million tokens, $0.050 cache read, $1.252 cache write per million tokens, 272K tokens of context
• GPT 6.1 Terra Pro: declared precision provider-managed, us, $1.002 input and $5.011 output per million tokens, $0.050 cache read per million tokens, 272K tokens of context
• GPT Audio: declared precision provider-managed, us, $2.496 input and $9.982 output per million tokens, $2.496 cache read per million tokens, 128K tokens of context
• GPT Latest: declared precision provider-managed, us, $10.007 input and $50.037 output per million tokens, $1.001 cache read per million tokens, 272K tokens of context
• GPT: Astra Latest: declared precision provider-managed, us, $10.017 input and $50.083 output per million tokens, $1.002 cache read per million tokens, 272K tokens of context
• GPT: Audio 2025 08 28: declared precision provider-managed, us, $2.494 input and $9.978 output per million tokens, $2.494 cache read per million tokens, 128K tokens of context
• GPT: Chat Latest: declared precision provider-managed, us, $2.001 input and $10.004 output per million tokens, $0.100 cache read per million tokens, 272K tokens of context
• GPT: Luna Latest: declared precision provider-managed, us, $0.100 input and $0.500 output per million tokens, $0.0100 cache read per million tokens, 272K tokens of context
• GPT: OSS Safeguard 20B: declared precision provider-managed, us, $0.075 input and $0.299 output per million tokens, $0.075 cache read per million tokens, 131.1K tokens of context
• GPT: Sol Latest: declared precision provider-managed, us, $1.997 input and $9.987 output per million tokens, $0.100 cache read per million tokens, 272K tokens of context
• GPT: Terra Latest: declared precision provider-managed, us, $1.000 input and $4.999 output per million tokens, $0.050 cache read per million tokens, 272K tokens of context
• Granite 4.2 30B: declared precision provider-managed, us, $0.160 input and $0.650 output per million tokens, $0.160 cache read per million tokens, 131.1K tokens of context
• Granite 4.2 3B: declared precision provider-managed, us, $0.030 input and $0.120 output per million tokens, $0.030 cache read per million tokens, 131.1K tokens of context
• Granite 4.2 8B: declared precision provider-managed, us, $0.060 input and $0.150 output per million tokens, $0.015 cache read per million tokens, 131.1K tokens of context
• Grayline: Qwen 3 8B: declared precision provider-managed, us, $0.299 input and $0.299 output per million tokens, $0.299 cache read per million tokens, 32.8K tokens of context
• Grok 3: declared precision provider-managed, us, $3.004 input and $15.021 output per million tokens, $0.751 cache read per million tokens, 131.1K tokens of context
• Grok 3 Beta: declared precision provider-managed, us, $3.006 input and $15.031 output per million tokens, $0.752 cache read per million tokens, 131.1K tokens of context
• Grok 3 Fast Beta: declared precision provider-managed, us, $4.990 input and $24.952 output per million tokens, $1.248 cache read per million tokens, 131.1K tokens of context
• Grok 3 Fast Latest: declared precision provider-managed, us, $4.989 input and $24.947 output per million tokens, $1.247 cache read per million tokens, 131.1K tokens of context
• Grok 3 Latest: declared precision provider-managed, us, $2.997 input and $14.985 output per million tokens, $0.749 cache read per million tokens, 131.1K tokens of context
• Grok 3 Mini Beta: declared precision provider-managed, us, $1.249 input and $2.498 output per million tokens, $0.200 cache read per million tokens, 131K tokens of context
• Grok 3 Mini Fast: declared precision provider-managed, us, $0.601 input and $4.003 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context
• Grok 3 Mini Fast Beta: declared precision provider-managed, us, $0.600 input and $3.997 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context
• Grok 3 Mini Fast Latest: declared precision provider-managed, us, $0.599 input and $3.991 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context
• Grok 3 Mini Latest: declared precision provider-managed, us, $0.299 input and $0.499 output per million tokens, $0.075 cache read per million tokens, 131.1K tokens of context
• Grok 4: declared precision provider-managed, us, $3.000 input and $15.002 output per million tokens, $3.000 cache read per million tokens, 256K tokens of context
• Grok 4 0709: declared precision provider-managed, us, $2.998 input and $14.989 output per million tokens, $2.998 cache read per million tokens, 128K tokens of context
• Grok 4 Fast: declared precision provider-managed, us, $0.200 input and $0.501 output per million tokens, $0.050 cache read per million tokens, 2M tokens of context
• Grok 4 Fast Non Reasoning: declared precision provider-managed, us, $0.200 input and $0.499 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4 Fast Reasoning: declared precision provider-managed, us, $0.200 input and $0.501 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4 Latest: declared precision provider-managed, us, $3.005 input and $15.027 output per million tokens, $3.005 cache read per million tokens, 128K tokens of context
• Grok 4.1 Fast: declared precision provider-managed, us, $0.200 input and $0.499 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4.1 Fast Non Reasoning: declared precision provider-managed, us, $0.200 input and $0.499 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4.1 Fast Non Reasoning Latest: declared precision provider-managed, us, $0.200 input and $0.500 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4.1 Fast Reasoning: declared precision provider-managed, us, $0.200 input and $0.501 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4.1 Fast Reasoning Latest: declared precision provider-managed, us, $0.200 input and $0.501 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Grok 4.20: declared precision provider-managed, us, $1.251 input and $2.502 output per million tokens, $0.200 cache read per million tokens, 2M tokens of context
• Grok 4.20 Beta 0309 Non Reasoning: declared precision provider-managed, us, $2.003 input and $6.008 output per million tokens, $0.200 cache read per million tokens, 2M tokens of context
• Grok 4.20 Beta 0309 Reasoning: declared precision provider-managed, us, $2.005 input and $6.015 output per million tokens, $0.200 cache read per million tokens, 2M tokens of context
• Grok 4.20 Multi Agent: declared precision provider-managed, us, $1.248 input and $2.496 output per million tokens, $0.200 cache read per million tokens, 2M tokens of context
• Grok 4.3: declared precision provider-managed, us, $1.251 input and $2.502 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Grok 4.3 Latest: declared precision provider-managed, us, $1.249 input and $2.498 output per million tokens, $0.200 cache read per million tokens, 200K tokens of context
• Grok 4.7: declared precision provider-managed, us, $1.996 input and $5.989 output per million tokens, $0.499 cache read per million tokens, 200K tokens of context
• Grok: Code Fast: declared precision provider-managed, us, $0.200 input and $1.499 output per million tokens, $0.020 cache read per million tokens, 256K tokens of context
• Grok: Code Fast 1: declared precision provider-managed, us, $0.200 input and $1.498 output per million tokens, $0.020 cache read per million tokens, 256K tokens of context
• Grok: Code Fast 1 0825: declared precision provider-managed, us, $0.200 input and $1.499 output per million tokens, $0.020 cache read per million tokens, 256K tokens of context
• Grok: Imagine Image: declared precision provider-managed, us, $0.020 per image, 32K tokens of context
• H3 Max: declared precision provider-managed, us, $0.080 per second, 32K tokens of context
• Hermes 3 Llama 3.1 70B: declared precision provider-managed, us, $0.701 input and $0.701 output per million tokens, $0.701 cache read per million tokens, 131.1K tokens of context
• Hermes High: declared precision provider-managed, us, $0.600 input and $1.100 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Hermes Low: declared precision provider-managed, us, $0.599 input and $1.098 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Hermes Medium: declared precision provider-managed, us, $0.600 input and $1.100 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Hidream I1 Full: declared precision provider-managed, us, $0.015 per image, 32K tokens of context
• Hidream O1 Image: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Hidream O1 Image Dev: declared precision provider-managed, us, $0.020 per image, 32K tokens of context
• Holo 3 35B a3b: declared precision provider-managed, us, $0.250 input and $1.799 output per million tokens, $0.250 cache read per million tokens, 65.5K tokens of context
• Holo 3 35B a3b:thinking: declared precision provider-managed, us, $0.250 input and $1.801 output per million tokens, $0.250 cache read per million tokens, 65.5K tokens of context
• hy3: declared precision provider-managed, us, $0.066 input and $0.260 output per million tokens, $0.029 cache read per million tokens, 262.1K tokens of context
• hy4: declared precision provider-managed, us, $0.462 input and $1.385 output per million tokens, $0.023 cache read per million tokens, 1M tokens of context
• Ideogram V2: declared precision provider-managed, us, $0.136 per image, 32K tokens of context
• Ideogram V2 Turbo: declared precision provider-managed, us, $0.085 per image, 32K tokens of context
• Ideogram V4.5: declared precision provider-managed, us, $0.060 per image, 32K tokens of context
• Inkling: declared precision provider-managed, us, $1.001 input and $4.053 output per million tokens, $0.170 cache read per million tokens, 1M tokens of context
• Inkling Small: declared precision provider-managed, us, $0.450 input and $1.200 output per million tokens, $0.450 cache read per million tokens, 524.3K tokens of context
• Inkling Small:thinking: declared precision provider-managed, us, $0.449 input and $1.197 output per million tokens, $0.100 cache read per million tokens, 524.3K tokens of context
• Inkling:thinking: declared precision provider-managed, us, $1.001 input and $4.053 output per million tokens, $0.170 cache read per million tokens, 1M tokens of context
• Jamba 1.5 Large: declared precision provider-managed, us, $1.995 input and $7.980 output per million tokens, $1.995 cache read per million tokens, 256K tokens of context
• Jamba 1.5 Mini: declared precision provider-managed, us, $0.200 input and $0.400 output per million tokens, $0.200 cache read per million tokens, 256K tokens of context
• Juggernaut: Pro Flux: declared precision provider-managed, us, $0.017 per image, 32K tokens of context
• K2 Think: declared precision provider-managed, us, $0.170 input and $0.681 output per million tokens, $0.170 cache read per million tokens, 128K tokens of context
• Kandinsky 6 Lite: declared precision provider-managed, us, $0.032 per second, 32K tokens of context
• Kandinsky 6 Pro: declared precision provider-managed, us, $0.270 per second, 32K tokens of context
• Kimi K2 Instruct: declared precision provider-managed, us, $0.401 input and $1.804 output per million tokens, $0.401 cache read per million tokens, 256K tokens of context
• Kimi K2 Instruct 0711: declared precision provider-managed, us, $0.400 input and $1.800 output per million tokens, $0.400 cache read per million tokens, 128K tokens of context
• Kimi K2 Instruct 0905: declared precision provider-managed, us, $0.400 input and $1.799 output per million tokens, $0.400 cache read per million tokens, 262.1K tokens of context
• Kimi K2 Instruct Fast: declared precision provider-managed, us, $0.401 input and $1.804 output per million tokens, $0.401 cache read per million tokens, 131.1K tokens of context
• Kimi K2 Instruct FP4: declared precision provider-managed, us, $0.400 input and $1.798 output per million tokens, $0.400 cache read per million tokens, 131.1K tokens of context
• Kimi k2.5:thinking: declared precision provider-managed, us, $0.375 input and $1.998 output per million tokens, $0.070 cache read per million tokens, 262.1K tokens of context
• Kimi k2.6:thinking: declared precision provider-managed, us, $0.389 input and $1.639 output per million tokens, $0.066 cache read per million tokens, 262.1K tokens of context
• Kimi K2.8 Preview: declared precision provider-managed, us, $0.998 input and $3.991 output per million tokens, $0.249 cache read per million tokens, 1M tokens of context
• Kimi K3.1 Pro Highspeed: declared precision provider-managed, us, $3.998 input and $19.991 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Kimi Latest: declared precision provider-managed, us, $1.999 input and $9.993 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Kling V3 4k: declared precision provider-managed, us, $0.419 per second, 32K tokens of context
• Kling V3 Turbo Pro: declared precision provider-managed, us, $0.140 per second, 32K tokens of context
• Kling V3 Turbo Standard: declared precision provider-managed, us, $0.112 per second, 32K tokens of context
• L3 8B Stheno V3.2: declared precision provider-managed, us, $0.050 input and $0.050 output per million tokens, $0.050 cache read per million tokens, 8,192 tokens of context
• L3.1 70B Celeste V0.1 BF16: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 32.8K tokens of context
• L3.1 70B Euryale V2.2: declared precision provider-managed, us, $0.306 input and $0.357 output per million tokens, $0.306 cache read per million tokens, 20.5K tokens of context
• L3.1 70B Hanami X1: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 32.8K tokens of context
• L3.3 70B Euryale V2.3: declared precision provider-managed, us, $0.492 input and $0.492 output per million tokens, $0.492 cache read per million tokens, 20.5K tokens of context
• L3.3: Cu Mai R1 70B: declared precision provider-managed, us, $0.493 input and $0.493 output per million tokens, $0.493 cache read per million tokens, 32.8K tokens of context
• L3.3: Electra R1 70B: declared precision provider-managed, us, $0.700 input and $0.700 output per million tokens, $0.700 cache read per million tokens, 32.8K tokens of context
• L3.3: Ms Nevoria 70B: declared precision provider-managed, us, $0.492 input and $0.492 output per million tokens, $0.492 cache read per million tokens, 32.8K tokens of context
• L3.3: Nevoria R1 70B: declared precision provider-managed, us, $0.492 input and $0.492 output per million tokens, $0.492 cache read per million tokens, 32.8K tokens of context
• Labs: Devstral Small 2512: declared precision provider-managed, us, $0.100 input and $0.300 output per million tokens, $0.100 cache read per million tokens, 256K tokens of context
• Lfm 2.5 2.6B: declared precision provider-managed, us, $0.100 input and $0.200 output per million tokens, $0.100 cache read per million tokens, 128K tokens of context
• Lfm 2.5 24B a2b: declared precision provider-managed, us, $0.050 input and $0.701 output per million tokens, $0.025 cache read per million tokens, 128K tokens of context
• Lightonocr 2 1B: declared precision provider-managed, us, $0.179 input and $0.347 output per million tokens, $0.179 cache read per million tokens, 32.8K tokens of context
• Lightricks: Ltx 2 Fast: declared precision provider-managed, us, $0.040 per second, 32K tokens of context
• Lightricks: Ltx 2 Pro: declared precision provider-managed, us, $0.060 per second, 32K tokens of context
• Ling 3.0 Flash: declared precision provider-managed, us, $0.060 input and $0.180 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Ling 3.0 Flash Fin: declared precision provider-managed, us, $0.060 input and $0.180 output per million tokens, $0.060 cache read per million tokens, 262.1K tokens of context
• Ling 3.0 Flash VL: declared precision provider-managed, us, $0.060 input and $0.180 output per million tokens, $0.012 cache read per million tokens, 262.1K tokens of context
• Ling 3.0 Flash:thinking: declared precision provider-managed, us, $0.075 input and $0.220 output per million tokens, $0.015 cache read per million tokens, 262.1K tokens of context
• Ling 3.1 Flash: declared precision provider-managed, us, $0.075 input and $0.220 output per million tokens, $0.015 cache read per million tokens, 262.1K tokens of context
• Llama 3 8B Instruct: declared precision provider-managed, us, $0.030 input and $0.060 output per million tokens, $0.030 cache read per million tokens, 8,192 tokens of context
• Llama 3.05 Nemotron Tenyxchat Storybreaker 70B: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 16.4K tokens of context
• Llama 3.05 Nt Storybreaker Ministral 70B: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 16.4K tokens of context
• Llama 3.1 70B Instruct: declared precision provider-managed, us, $0.399 input and $0.399 output per million tokens, $0.399 cache read per million tokens, 131.1K tokens of context
• Llama 3.1 8B Instruct: declared precision provider-managed, us, $0.020 input and $0.040 output per million tokens, $0.020 cache read per million tokens, 131.1K tokens of context
• Llama 3.1 Nemotron 70B Instruct: declared precision provider-managed, us, $0.600 input and $0.600 output per million tokens, $0.600 cache read per million tokens, 131.1K tokens of context
• Llama 3.1 Nemotron 70B Instruct Hf: declared precision provider-managed, us, $0.357 input and $0.408 output per million tokens, $0.357 cache read per million tokens, 16.4K tokens of context
• Llama 3.2 3B Instruct: declared precision provider-managed, us, $0.020 input and $0.020 output per million tokens, $0.020 cache read per million tokens, 131.1K tokens of context
• Llama 3.3 70B Instruct Abliterated: declared precision provider-managed, us, $0.700 input and $0.700 output per million tokens, $0.700 cache read per million tokens, 32.8K tokens of context
• Llama 3.3 Nemotron Super 49B V1: declared precision provider-managed, us, $0.150 input and $0.150 output per million tokens, $0.150 cache read per million tokens, 128K tokens of context
• Llama 4 Maverick: declared precision provider-managed, us, $0.150 input and $0.599 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
• Llama 4 Maverick 17B 128e Instruct FP8: declared precision provider-managed, us, $0.270 input and $0.850 output per million tokens, $0.270 cache read per million tokens, 1M tokens of context
• Llama 4 Scout: declared precision provider-managed, us, $0.085 input and $0.460 output per million tokens, $0.085 cache read per million tokens, 328K tokens of context
• Llama 4 Scout 17B 16e Instruct: declared precision provider-managed, us, $0.100 input and $0.301 output per million tokens, $0.100 cache read per million tokens, 327.7K tokens of context
• Llama: Guard 3 8B: declared precision provider-managed, us, $0.055 input and $0.055 output per million tokens, $0.055 cache read per million tokens, 131.1K tokens of context
• Llama: Guard 4 12B: declared precision provider-managed, us, $0.180 input and $0.180 output per million tokens, $0.180 cache read per million tokens, 163.8K tokens of context
• Llama: Xlam 2 70B Fc R: declared precision provider-managed, us, $2.494 input and $2.494 output per million tokens, $2.494 cache read per million tokens, 128K tokens of context
• Long Form: declared precision provider-managed, us, $0.000100 per character, 4,097 tokens of context
• Longcat 2.0: declared precision provider-managed, us, $0.750 input and $3.002 output per million tokens, $0.015 cache read per million tokens, 1M tokens of context
• Longcat 2.0:thinking: declared precision provider-managed, us, $0.751 input and $3.003 output per million tokens, $0.015 cache read per million tokens, 1M tokens of context
• Longcat 2.5 Preview: declared precision provider-managed, us, $0.787 input and $3.097 output per million tokens, $0.016 cache read per million tokens, 1M tokens of context
• Longcat Image: declared precision provider-managed, us, $0.150 per image, 32K tokens of context
• Ltxv 2: declared precision provider-managed, us, $0.060 per second, 32K tokens of context
• Ltxv 2 Fast: declared precision provider-managed, us, $0.040 per second, 32K tokens of context
• Lumimaid V0.2 70B: declared precision provider-managed, us, $1.002 input and $1.504 output per million tokens, $1.002 cache read per million tokens, 16.4K tokens of context
• M1: declared precision provider-managed, us, $0.400 input and $2.203 output per million tokens, $0.400 cache read per million tokens, 200K tokens of context
• Magidonia 24B V4.3: declared precision provider-managed, us, $0.100 input and $0.121 output per million tokens, $0.100 cache read per million tokens, 32.8K tokens of context
• Magnum V2 72B: declared precision provider-managed, us, $2.003 input and $2.987 output per million tokens, $2.003 cache read per million tokens, 16.4K tokens of context
• Magnum V4 72B: declared precision provider-managed, us, $2.644 input and $5.288 output per million tokens, $2.644 cache read per million tokens, 16.4K tokens of context
• Manta: Flash 1.0: declared precision provider-managed, us, $0.020 input and $0.160 output per million tokens, $0.020 cache read per million tokens, 16.4K tokens of context
• Manta: Mini 1.0: declared precision provider-managed, us, $0.020 input and $0.160 output per million tokens, $0.020 cache read per million tokens, 8,192 tokens of context
• Manta: Pro 1.0: declared precision provider-managed, us, $0.060 input and $0.500 output per million tokens, $0.060 cache read per million tokens, 65.5K tokens of context
• Mercury 2: declared precision provider-managed, us, $0.250 input and $0.750 output per million tokens, $0.025 cache read per million tokens, 128K tokens of context
• Mercury 2.5 Preview: declared precision provider-managed, us, $0.040 input and $0.150 output per million tokens, $0.0040 cache read per million tokens, 260K tokens of context
• Mercury 3: declared precision provider-managed, us, $0.100 input and $0.350 output per million tokens, $0.0100 cache read per million tokens, 1M tokens of context
• Mercury: Coder Small: declared precision provider-managed, us, $0.250 input and $1.001 output per million tokens, $0.250 cache read per million tokens, 32.8K tokens of context
• Meta: Llama 3 70B Instruct Abliterated V3.5: declared precision provider-managed, us, $0.701 input and $0.701 output per million tokens, $0.701 cache read per million tokens, 8,192 tokens of context
• Meta: Llama 3.1 8B Instruct FP8: declared precision provider-managed, us, $0.020 input and $0.040 output per million tokens, $0.020 cache read per million tokens, 128K tokens of context
• Mimo V2.5 Pro:thinking: declared precision provider-managed, us, $0.489 input and $0.969 output per million tokens, $0.0040 cache read per million tokens, 1M tokens of context
• Mimo v2.5:thinking: declared precision provider-managed, us, $0.421 input and $2.107 output per million tokens, $0.084 cache read per million tokens, 1M tokens of context
• Mimo V2.6 Flash Abliterated: declared precision provider-managed, us, $0.500 input and $1.500 output per million tokens, $0.275 cache read per million tokens, 1M tokens of context
• Mimo V2.6 Flash Rl: declared precision provider-managed, us, $0.140 input and $0.281 output per million tokens, $0.140 cache read per million tokens, 1M tokens of context
• Mimo V2.6 Flash Uncensored: declared precision provider-managed, us, $0.501 input and $1.502 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Mimo V2.6 Flash Uncensored:thinking: declared precision provider-managed, us, $0.500 input and $1.500 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Mimo V2.6 Pro Rl: declared precision provider-managed, us, $0.434 input and $0.868 output per million tokens, $0.434 cache read per million tokens, 1M tokens of context
• MiniMax 01: declared precision provider-managed, us, $0.140 input and $1.123 output per million tokens, $0.140 cache read per million tokens, 1M tokens of context
• MiniMax Latest: declared precision provider-managed, us, $0.230 input and $0.960 output per million tokens, $0.050 cache read per million tokens, 512K tokens of context
• MiniMax M1: declared precision provider-managed, us, $0.140 input and $1.335 output per million tokens, $0.140 cache read per million tokens, 1M tokens of context
• MiniMax M1 80k: declared precision provider-managed, us, $0.549 input and $2.198 output per million tokens, $0.549 cache read per million tokens, 1M tokens of context
• MiniMax M2.1: declared precision provider-managed, us, $0.300 input and $1.199 output per million tokens, $0.030 cache read per million tokens, 200K tokens of context
• MiniMax M2.7 Turbo: declared precision provider-managed, us, $0.599 input and $2.395 output per million tokens, $0.599 cache read per million tokens, 204.8K tokens of context
• MiniMax m3:thinking: declared precision provider-managed, us, $0.231 input and $0.962 output per million tokens, $0.050 cache read per million tokens, 512K tokens of context
• MiniMax: Hailuo 02: declared precision provider-managed, us, $0.060 per second, 32K tokens of context
• MiniMax: Hailuo 02 Pro: declared precision provider-managed, us, $0.090 per second, 32K tokens of context
• MiniMax: Hailuo 23 Pro: declared precision provider-managed, us, $0.098 per second, 32K tokens of context
• Ministral 14B 2512: declared precision provider-managed, us, $0.200 input and $0.200 output per million tokens, $0.200 cache read per million tokens, 262.1K tokens of context
• Ministral 14B Instruct 2512: declared precision provider-managed, us, $0.100 input and $0.400 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
• Ministral 3B 2512: declared precision provider-managed, us, $0.100 input and $0.100 output per million tokens, $0.100 cache read per million tokens, 131.1K tokens of context
• Ministral 8B 2512: declared precision provider-managed, us, $0.150 input and $0.150 output per million tokens, $0.150 cache read per million tokens, 262.1K tokens of context
• Mistral Large: declared precision provider-managed, us, $2.003 input and $5.993 output per million tokens, $0.200 cache read per million tokens, 128K tokens of context
• Mistral Saba: declared precision provider-managed, us, $0.199 input and $0.596 output per million tokens, $0.199 cache read per million tokens, 32.8K tokens of context
• Mistral Small: declared precision provider-managed, us, $0.100 input and $0.300 output per million tokens, $0.100 cache read per million tokens, 32K tokens of context
• Mistral Tiny: declared precision provider-managed, us, $0.250 input and $0.250 output per million tokens, $0.250 cache read per million tokens, 32K tokens of context
• Mistral: Code Agent Latest: declared precision provider-managed, us, $0.400 input and $2.000 output per million tokens, $0.400 cache read per million tokens, 262.1K tokens of context
• Mistral: Code Latest: declared precision provider-managed, us, $0.300 input and $0.901 output per million tokens, $0.300 cache read per million tokens, 256K tokens of context
• Mistral: Large 2402: declared precision provider-managed, us, $3.998 input and $11.994 output per million tokens, $3.998 cache read per million tokens, 32K tokens of context
• Mistral: Large 4: declared precision provider-managed, us, $0.679 input and $2.088 output per million tokens, $0.070 cache read per million tokens, 524.3K tokens of context
• Mistral: Medium 2312: declared precision provider-managed, us, $2.695 input and $8.085 output per million tokens, $2.695 cache read per million tokens, 32K tokens of context
• Mistral: Medium 3: declared precision provider-managed, us, $0.400 input and $2.002 output per million tokens, $0.400 cache read per million tokens, 131.1K tokens of context
• Mistral: Medium 3.1: declared precision provider-managed, us, $0.400 input and $1.999 output per million tokens, $0.400 cache read per million tokens, 131.1K tokens of context
• Mistral: Medium 3.5: declared precision provider-managed, us, $1.498 input and $7.490 output per million tokens, $1.498 cache read per million tokens, 256K tokens of context
• Mistral: Medium 3.5:thinking: declared precision provider-managed, us, $1.503 input and $7.514 output per million tokens, $1.503 cache read per million tokens, 256K tokens of context
• Mistral: Nemo Instruct 2407: declared precision provider-managed, us, $0.100 input and $0.121 output per million tokens, $0.100 cache read per million tokens, 16.4K tokens of context
• Mistral: Small 24B Instruct 2501: declared precision provider-managed, us, $0.116 input and $0.347 output per million tokens, $0.116 cache read per million tokens, 32.8K tokens of context
• Mistral: Small 3.1 24B Instruct: declared precision provider-managed, us, $0.100 input and $0.300 output per million tokens, $0.100 cache read per million tokens, 128K tokens of context
• Mistral: Small 4 119B 2603:thinking: declared precision provider-managed, us, $0.400 input and $1.400 output per million tokens, $0.400 cache read per million tokens, 262.1K tokens of context
• Mixtral 8x22b Instruct V0.1: declared precision provider-managed, us, $2.000 input and $6.001 output per million tokens, $0.200 cache read per million tokens, 65.5K tokens of context
• Mixtral 8x7b Instruct V0.1: declared precision provider-managed, us, $0.401 input and $0.401 output per million tokens, $0.401 cache read per million tokens, 32.8K tokens of context
• Mn 12B Mag Mell R1: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 16.4K tokens of context
• Mn: Loosecannon 12B V1: declared precision provider-managed, us, $0.493 input and $0.493 output per million tokens, $0.493 cache read per million tokens, 16.4K tokens of context
• Moondream 3 Preview: declared precision provider-managed, us, $0.300 input and $2.500 output per million tokens, $0.300 cache read per million tokens, 32K tokens of context
• Moondream 3.1 9B a2b: declared precision provider-managed, us, $0.299 input and $2.495 output per million tokens, $0.299 cache read per million tokens, 32K tokens of context
• Morgana V1.2: declared precision provider-managed, us, $0.0100 per image, 32K tokens of context
• ms3.2 24B Magnum Diamond: declared precision provider-managed, us, $0.493 input and $0.493 output per million tokens, $0.493 cache read per million tokens, 32.8K tokens of context
• ms3.2: The Omega Directive 24B Unslop V2.0: declared precision provider-managed, us, $0.500 input and $0.500 output per million tokens, $0.500 cache read per million tokens, 32.8K tokens of context
• Muse Wonder: declared precision provider-managed, us, $4.007 input and $20.034 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• Muse: Spark 1.2 Contributor: declared precision provider-managed, us, $0.100 input and $0.200 output per million tokens, $0.0020 cache read per million tokens, 1M tokens of context
• Muse: Spark 1.3 Contributor: declared precision provider-managed, us, $0.100 input and $0.200 output per million tokens, $0.0020 cache read per million tokens, 1M tokens of context
• Muse: Spark Open: declared precision provider-managed, us, $1.249 input and $4.247 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
• Muse: Spark Open 816B a42b:baseten: declared precision provider-managed, us, $1.251 input and $4.252 output per million tokens, $1.251 cache read per million tokens, 1M tokens of context
• Mythomax L2 13B: declared precision provider-managed, us, $0.100 input and $0.100 output per million tokens, $0.100 cache read per million tokens, 4,096 tokens of context
• Nano: Banana 2: declared precision provider-managed, us, $0.080 per image, 32K tokens of context
• Nemomix: Unleashed 12B: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 32.8K tokens of context
• Nemotron 3 Super 120B a12b:thinking: declared precision provider-managed, us, $0.050 input and $0.250 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Nemotron 3 Ultra 550B a55b:thinking: declared precision provider-managed, us, $0.500 input and $2.499 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
• Nemotron 3.5 Content Safety: declared precision provider-managed, us, $0.050 input and $0.150 output per million tokens, $0.025 cache read per million tokens, 131.1K tokens of context
• Nemotron 3.5 Embed 1B BF16: declared precision provider-managed, us, $0.015 input per million tokens, 32.8K tokens of context
• Nemotron 3.5 Embed 8B BF16: declared precision provider-managed, us, $0.035 input per million tokens, 32.8K tokens of context
• Nemotron 3.5 Lightning:thinking: declared precision provider-managed, us, $0.050 input and $0.200 output per million tokens, $0.0100 cache read per million tokens, 1M tokens of context
• Nemotron 3.5 Super VL: declared precision provider-managed, us, $0.150 input and $0.500 output per million tokens, $0.020 cache read per million tokens, 262.1K tokens of context
• Nemotron: Nano 9B V2: declared precision provider-managed, us, $0.040 input and $0.160 output per million tokens, $0.040 cache read per million tokens, 131.1K tokens of context
• Nemotron: Sea Lion V4.8 120B a12b: declared precision provider-managed, us, $0.501 input and $2.003 output per million tokens, $0.501 cache read per million tokens, 262.1K tokens of context
• Neural: declared precision provider-managed, us, $0.000016 per character, 4,097 tokens of context
• Neuraldaredevil 8B Abliterated: declared precision provider-managed, us, $0.439 input and $0.439 output per million tokens, $0.439 cache read per million tokens, 8,192 tokens of context
• Nex N2.5 Mini: declared precision provider-managed, us, $0.025 input and $0.100 output per million tokens, $0.0025 cache read per million tokens, 262.1K tokens of context
• Nex N2.5 Pro: declared precision provider-managed, us, $0.075 input and $0.250 output per million tokens, $0.015 cache read per million tokens, 262.1K tokens of context
• Nova 2 Atc: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Automotive: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Conversationalai: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Drivethru: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context, the cheapest of 2 offers
• Nova 2 Finance: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 General: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Meeting: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Phonecall: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Video: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 2 Voicemail: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 3: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context, the cheapest of 2 offers
• Nova 3 General: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova 3 Medical: declared precision provider-managed, us, $0.000087 per second, 1 tokens of context
• Nova General: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova Phonecall: declared precision provider-managed, us, $0.000072 per second, 1 tokens of context
• Nova: Lite V1: declared precision provider-managed, us, $0.059 input and $0.238 output per million tokens, $0.059 cache read per million tokens, 300K tokens of context
• Nova: Pro V1: declared precision provider-managed, us, $0.799 input and $3.196 output per million tokens, $0.799 cache read per million tokens, 300K tokens of context
• Nvidia: Nemotron 3 Ultra 550B a55b BF16: declared precision provider-managed, us, $1.001 input and $5.003 output per million tokens, $1.001 cache read per million tokens, 262.1K tokens of context
• Nvidia: Nemotron 3.5 Super VL 120B a12b Nvfp 4:baseten: declared precision provider-managed, us, $0.200 input and $0.500 output per million tokens, $0.200 cache read per million tokens, 1M tokens of context
• O1: declared precision provider-managed, us, $14.984 input and $59.937 output per million tokens, $7.492 cache read per million tokens, 200K tokens of context
• O1 Mini: declared precision provider-managed, us, $1.209 input and $4.836 output per million tokens, $0.605 cache read per million tokens, 128K tokens of context
• O1 Pro: declared precision provider-managed, us, $149.822 input and $599.289 output per million tokens, $74.911 cache read per million tokens, 200K tokens of context
• O3: declared precision provider-managed, us, $1.997 input and $7.987 output per million tokens, $0.998 cache read per million tokens, 200K tokens of context
• O3 2025 04 16: declared precision provider-managed, us, $2.004 input and $8.016 output per million tokens, $0.501 cache read per million tokens, 200K tokens of context
• O3 Mini: declared precision provider-managed, us, $1.100 input and $4.400 output per million tokens, $0.550 cache read per million tokens, 200K tokens of context
• O3: Deep Research: declared precision provider-managed, us, $10.024 input and $40.096 output per million tokens, $2.506 cache read per million tokens, 200K tokens of context
• O3: Deep Research 2025 06 26: declared precision provider-managed, us, $9.988 input and $39.951 output per million tokens, $2.497 cache read per million tokens, 200K tokens of context
• O3: Mini Low: declared precision provider-managed, us, $1.098 input and $4.394 output per million tokens, $0.549 cache read per million tokens, 200K tokens of context
• O3: Pro 2025 06 10: declared precision provider-managed, us, $22.044 input and $88.177 output per million tokens, $11.022 cache read per million tokens, 200K tokens of context
• O4: Mini Deep Research: declared precision provider-managed, us, $2.000 input and $8.000 output per million tokens, $0.500 cache read per million tokens, 200K tokens of context
• O4: Mini Deep Research 2025 06 26: declared precision provider-managed, us, $2.001 input and $8.005 output per million tokens, $0.500 cache read per million tokens, 200K tokens of context
• Olmocr 7B 0725 FP8: declared precision provider-managed, us, $0.270 input and $1.501 output per million tokens, $0.270 cache read per million tokens, 16.4K tokens of context
• Open: Mistral 7B: declared precision provider-managed, us, $0.250 input and $0.250 output per million tokens, $0.250 cache read per million tokens, 32K tokens of context
• Open: Mixtral 8x22b: declared precision provider-managed, us, $2.003 input and $6.009 output per million tokens, $2.003 cache read per million tokens, 65.3K tokens of context
• Open: Mixtral 8x7b: declared precision provider-managed, us, $0.701 input and $0.701 output per million tokens, $0.701 cache read per million tokens, 32K tokens of context
• Openreasoning: Nemotron 32B: declared precision provider-managed, us, $0.100 input and $0.400 output per million tokens, $0.100 cache read per million tokens, 32.8K tokens of context
• Orcacyber: Zero 1.5: declared precision provider-managed, us, $2.996 input and $7.490 output per million tokens, $0.749 cache read per million tokens, 999.5K tokens of context
• Ornith 1.5 122B: declared precision provider-managed, us, $0.260 input and $2.080 output per million tokens, $0.070 cache read per million tokens, 262.1K tokens of context
• Ornith 1.5 35B a3b: declared precision provider-managed, us, $0.100 input and $0.400 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Ornith 1.5 35B a3b:thinking: declared precision provider-managed, us, $0.100 input and $0.399 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• P Video: declared precision provider-managed, us, $0.020 per second, 32K tokens of context
• Pareto 26.10: declared precision provider-managed, us, $0.800 input and $3.200 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Pareto 26.9: declared precision provider-managed, us, $2.496 input and $7.487 output per million tokens, $0.250 cache read per million tokens, 262.1K tokens of context
• Particle 1: declared precision provider-managed, us, $0.250 input and $0.998 output per million tokens, $0.030 cache read per million tokens, 1M tokens of context
• Perceptron mk1: declared precision provider-managed, us, $0.150 input and $1.497 output per million tokens, $0.150 cache read per million tokens, 32.8K tokens of context
• Perceptron mk1.5: declared precision provider-managed, us, $0.150 input and $1.503 output per million tokens, $0.150 cache read per million tokens, 36.9K tokens of context
• Phi 4: declared precision provider-managed, us, $0.070 input and $0.140 output per million tokens, $0.070 cache read per million tokens, 16.4K tokens of context
• Phi 4 Mini Instruct: declared precision provider-managed, us, $0.170 input and $0.681 output per million tokens, $0.170 cache read per million tokens, 128K tokens of context
• Phi 4 Multimodal Instruct: declared precision provider-managed, us, $0.070 input and $0.110 output per million tokens, $0.070 cache read per million tokens, 128K tokens of context
• Pixtral 12B 2409: declared precision provider-managed, us, $0.150 input and $0.150 output per million tokens, $0.150 cache read per million tokens, 128K tokens of context
• Playground V2.5: declared precision provider-managed, us, $0.0085 per image, 32K tokens of context
• Pokee Isaac: declared precision provider-managed, us, $0.150 input and $0.998 output per million tokens, $0.150 cache read per million tokens, 250K tokens of context
• Proteus: declared precision provider-managed, us, $0.0034 per image, 32K tokens of context
• Qwen 2 5 VL 72B Instruct: declared precision provider-managed, us, $0.698 input and $0.698 output per million tokens, $0.698 cache read per million tokens, 32K tokens of context
• Qwen 2.5 32B Instruct Abliterated: declared precision provider-managed, us, $0.700 input and $0.700 output per million tokens, $0.700 cache read per million tokens, 32.8K tokens of context
• Qwen 2.5 72B Instruct: declared precision provider-managed, us, $0.359 input and $0.399 output per million tokens, $0.359 cache read per million tokens, 32.8K tokens of context, the cheapest of 2 offers
• Qwen 2.5 7B Instruct: declared precision provider-managed, us, $0.040 input and $0.100 output per million tokens, $0.040 cache read per million tokens, 32.8K tokens of context
• Qwen 2.5 Coder 32B Instruct: declared precision provider-managed, us, $0.201 input and $0.201 output per million tokens, $0.201 cache read per million tokens, 32K tokens of context
• Qwen 2.5 VL 32B Instruct: declared precision provider-managed, us, $0.200 input and $0.600 output per million tokens, $0.200 cache read per million tokens, 128K tokens of context
• Qwen 3 235B a22b: declared precision provider-managed, us, $0.090 input and $0.549 output per million tokens, $0.090 cache read per million tokens, 262.1K tokens of context
• Qwen 3 235B a22b Instruct 2507: declared precision provider-managed, us, $0.090 input and $0.550 output per million tokens, $0.090 cache read per million tokens, 262.1K tokens of context
• Qwen 3 235B a22b Thinking 2507: declared precision provider-managed, us, $0.300 input and $0.499 output per million tokens, $0.300 cache read per million tokens, 131.1K tokens of context
• Qwen 3 30B a3b Instruct 2507: declared precision provider-managed, us, $0.200 input and $0.499 output per million tokens, $0.200 cache read per million tokens, 256K tokens of context
• Qwen 3 Coder 30B a3b Instruct: declared precision provider-managed, us, $0.100 input and $0.400 output per million tokens, $0.100 cache read per million tokens, 128K tokens of context
• Qwen 3 Coder 480B a35b Instruct: declared precision provider-managed, us, $0.400 input and $1.601 output per million tokens, $0.400 cache read per million tokens, 262.1K tokens of context
• Qwen 3 Coder Next: declared precision provider-managed, us, $0.120 input and $0.801 output per million tokens, $0.070 cache read per million tokens, 262.1K tokens of context
• Qwen 3 Embedding 4B: declared precision provider-managed, us, $0.020 input per million tokens, 32.8K tokens of context
• Qwen 3 Embedding 8B: declared precision provider-managed, us, $0.010 input per million tokens, 32.8K tokens of context
• Qwen 3 Next 80B a3b Instruct: declared precision provider-managed, us, $0.090 input and $1.098 output per million tokens, $0.090 cache read per million tokens, 262.1K tokens of context
• Qwen 3 Next 80B a3b Thinking: declared precision provider-managed, us, $0.150 input and $0.651 output per million tokens, $0.150 cache read per million tokens, 256K tokens of context
• Qwen 3 VL 30B a3b Instruct: declared precision provider-managed, us, $0.150 input and $0.599 output per million tokens, $0.150 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 122B a10b:thinking: declared precision provider-managed, us, $0.261 input and $2.085 output per million tokens, $0.261 cache read per million tokens, 131.1K tokens of context
• Qwen 3.5 27B Blossom V6.4 Derestricted: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 27B Bluestar V3 Derestricted: declared precision provider-managed, us, $0.307 input and $0.307 output per million tokens, $0.307 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted: declared precision provider-managed, us, $0.307 input and $0.307 output per million tokens, $0.031 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.031 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 27B Queen Derestricted: declared precision provider-managed, us, $0.306 input and $0.306 output per million tokens, $0.306 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 27b:thinking: declared precision provider-managed, us, $0.200 input and $1.751 output per million tokens, $0.020 cache read per million tokens, 260.1K tokens of context
• Qwen 3.5 35B a3b:thinking: declared precision provider-managed, us, $0.140 input and $1.001 output per million tokens, $0.050 cache read per million tokens, 260.1K tokens of context
• Qwen 3.5 397B a17b:thinking: declared precision provider-managed, us, $0.390 input and $2.342 output per million tokens, $0.390 cache read per million tokens, 262.1K tokens of context
• Qwen 3.5 Flash:thinking: declared precision provider-managed, us, $0.100 input and $0.399 output per million tokens, $0.100 cache read per million tokens, 991.8K tokens of context
• Qwen 3.5 Plus 20260218: declared precision provider-managed, us, $0.400 input and $2.402 output per million tokens, $0.400 cache read per million tokens, 256K tokens of context
• Qwen 3.5 Plus:thinking: declared precision provider-managed, us, $0.400 input and $2.399 output per million tokens, $0.040 cache read per million tokens, 983.6K tokens of context
• Qwen 3.6 27b:thinking: declared precision provider-managed, us, $0.203 input and $2.242 output per million tokens, $0.203 cache read per million tokens, 262.1K tokens of context
• Qwen 3.6 35B a3b:thinking: declared precision provider-managed, us, $0.112 input and $0.800 output per million tokens, $0.112 cache read per million tokens, 1M tokens of context
• Qwen 3.6 Max Preview: declared precision provider-managed, us, $1.041 input and $6.243 output per million tokens, $1.041 cache read per million tokens, 245.8K tokens of context
• Qwen 3.7 Flash:thinking: declared precision provider-managed, us, $0.030 input and $0.130 output per million tokens, $0.0060 cache read per million tokens, 32K tokens of context
• Qwen 3.7 Max:thinking: declared precision provider-managed, us, $1.473 input and $4.418 output per million tokens, $0.295 cache read per million tokens, 1M tokens of context
• Qwen 3.7 Plus:thinking: declared precision provider-managed, us, $0.400 input and $1.602 output per million tokens, $0.080 cache read per million tokens, 256K tokens of context
• Qwen 3.8 27B Antislop: declared precision provider-managed, us, $0.100 input and $0.599 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Cybersecurity: declared precision provider-managed, us, $0.100 input and $0.599 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Darkidol: declared precision provider-managed, us, $0.100 input and $0.601 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Fable: declared precision provider-managed, us, $0.249 input and $1.496 output per million tokens, $0.125 cache read per million tokens, 524.3K tokens of context
• Qwen 3.8 27B Fimi: declared precision provider-managed, us, $0.100 input and $0.600 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Hemmingway: declared precision provider-managed, us, $0.249 input and $1.497 output per million tokens, $0.125 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Kimiko: declared precision provider-managed, us, $0.100 input and $0.601 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Kiwen: declared precision provider-managed, us, $0.100 input and $0.601 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Novelist: declared precision provider-managed, us, $0.100 input and $0.599 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Queen: declared precision provider-managed, us, $0.250 input and $1.499 output per million tokens, $0.125 cache read per million tokens, 524.3K tokens of context
• Qwen 3.8 27B Swift: declared precision provider-managed, us, $0.100 input and $0.601 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Synthia: declared precision provider-managed, us, $0.100 input and $0.599 output per million tokens, $0.050 cache read per million tokens, 262.1K tokens of context
• Qwen 3.8 27B Uncensored: declared precision provider-managed, us, $1.002 input and $3.007 output per million tokens, $0.221 cache read per million tokens, 1M tokens of context
• Qwen 3.8 27B Uncensored Fast: declared precision provider-managed, us, $0.998 input and $2.994 output per million tokens, $0.220 cache read per million tokens, 524.3K tokens of context
• Qwen 3.8 27B Uncensored:thinking: declared precision provider-managed, us, $0.998 input and $2.993 output per million tokens, $0.219 cache read per million tokens, 1M tokens of context
• Qwen 3.8 Flash Next FP8: declared precision provider-managed, us, $0.150 input and $0.471 output per million tokens, $0.150 cache read per million tokens, 1M tokens of context
• Qwen 3.8 Max Prime: declared precision provider-managed, us, $4.002 input and $12.005 output per million tokens, $0.500 cache read per million tokens, 1M tokens of context
• Qwen 3.8 Max:thinking: declared precision provider-managed, us, $2.004 input and $6.011 output per million tokens, $0.250 cache read per million tokens, 991K tokens of context
• Qwen Image: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Qwen Max: declared precision provider-managed, us, $1.597 input and $6.380 output per million tokens, $1.597 cache read per million tokens, 32K tokens of context
• Qwen Plus: declared precision provider-managed, us, $0.399 input and $1.199 output per million tokens, $0.399 cache read per million tokens, 995.9K tokens of context
• Qwen Turbo: declared precision provider-managed, us, $0.050 input and $0.200 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
• Qwen: Image 2.0 Pro: declared precision provider-managed, us, $0.075 per image, 32K tokens of context
• Qwen: Image 2512: declared precision provider-managed, us, $0.025 per image, 32K tokens of context
• Qwen: Image Max: declared precision provider-managed, us, $0.070 per image, 32K tokens of context
• Qwen: Sea Lion V4 32B It: declared precision provider-managed, us, $0.250 input and $0.501 output per million tokens, $0.250 cache read per million tokens, 32K tokens of context
• Qwen: Text Embedding V3: declared precision provider-managed, us, $0.070 input per million tokens, 8,192 tokens of context
• Qwen: Text Embedding V4: declared precision provider-managed, us, $0.070 input per million tokens, 8,192 tokens of context
• Qwerky 72B: declared precision provider-managed, us, $0.499 input and $0.499 output per million tokens, $0.499 cache read per million tokens, 32K tokens of context
• Qwq 32B: declared precision provider-managed, us, $0.150 input and $0.401 output per million tokens, $0.150 cache read per million tokens, 131.1K tokens of context
• Recraft V3: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Recraft V4: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Recraft V4 Pro: declared precision provider-managed, us, $0.250 per image, 32K tokens of context
• Recraft V4 Style: declared precision provider-managed, us, $0.038 per image, 32K tokens of context
• Recraft V4 Style Pro: declared precision provider-managed, us, $0.110 per image, 32K tokens of context
• Recraft V4.1: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Recraft V4.1 Flash: declared precision provider-managed, us, $0.0080 per image, 32K tokens of context
• Recraft V4.1 Pro: declared precision provider-managed, us, $0.249 per image, 32K tokens of context
• Recraft V4.1 Pro Text To Image Utility: declared precision provider-managed, us, $0.250 per image, 32K tokens of context
• Recraft V4.1 Text To Image Utility: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Reka: Edge 2603: declared precision provider-managed, us, $0.105 input and $0.105 output per million tokens, $0.105 cache read per million tokens, 16.4K tokens of context
• Remm: Slerp L2 13B: declared precision provider-managed, us, $0.799 input and $1.207 output per million tokens, $0.799 cache read per million tokens, 6,144 tokens of context
• Rev Animated: declared precision provider-managed, us, $0.0017 per image, 32K tokens of context
• Rocinante 12B V1.1: declared precision provider-managed, us, $0.409 input and $0.596 output per million tokens, $0.409 cache read per million tokens, 16.4K tokens of context
• Sarvam 105B: declared precision provider-managed, us, $0.054 input and $0.213 output per million tokens, $0.034 cache read per million tokens, 131.1K tokens of context
• Schematron V2 Small: declared precision provider-managed, us, $0.050 input and $0.230 output per million tokens, $0.050 cache read per million tokens, 128K tokens of context
• Schematron V2 Turbo: declared precision provider-managed, us, $0.030 input and $0.150 output per million tokens, $0.030 cache read per million tokens, 128K tokens of context
• sd3: declared precision provider-managed, us, $0.065 per image, 32K tokens of context
• Seedream 3.0: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Seedream 5.0 Lite Preview: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Seedream V5.0 Lite: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Seedream V5.0 Lite Sequential: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Shisa V2 Llama 3.3 70B: declared precision provider-managed, us, $0.500 input and $0.500 output per million tokens, $0.500 cache read per million tokens, 128K tokens of context
• Shisa V2.1 Llama 3.3 70B: declared precision provider-managed, us, $0.500 input and $0.500 output per million tokens, $0.500 cache read per million tokens, 32.8K tokens of context
• Solar: Mini 4: declared precision provider-managed, us, $0.050 input and $0.200 output per million tokens, $0.0050 cache read per million tokens, 524.3K tokens of context
• Solar: Mini 4:thinking: declared precision provider-managed, us, $0.050 input and $0.200 output per million tokens, $0.0050 cache read per million tokens, 524.3K tokens of context
• Solar: Pro 3: declared precision provider-managed, us, $0.150 input and $0.601 output per million tokens, $0.015 cache read per million tokens, 131.1K tokens of context
• Solar: Pro 4: declared precision provider-managed, us, $0.150 input and $0.600 output per million tokens, $0.030 cache read per million tokens, 524.3K tokens of context
• Solar: Pro 4:thinking: declared precision provider-managed, us, $0.150 input and $0.600 output per million tokens, $0.030 cache read per million tokens, 524.3K tokens of context
• Sonar: declared precision provider-managed, us, $1.001 input and $1.001 output per million tokens, $1.001 cache read per million tokens, 128K tokens of context
• Speech: To Text: declared precision provider-managed, us, $0.00012 per second, 1 tokens of context
• Stable: Diffusion 3 Large: declared precision provider-managed, us, $0.065 per image, 32K tokens of context
• Stable: Diffusion 3 Large Turbo: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Stable: Diffusion 3 Medium: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Stable: Diffusion 3.5 Large: declared precision provider-managed, us, $0.065 per image, 32K tokens of context, the cheapest of 2 offers
• Stable: Diffusion 3.5 Large Turbo: declared precision provider-managed, us, $0.040 per image, 32K tokens of context
• Stable: Diffusion 3.5 Medium: declared precision provider-managed, us, $0.035 per image, 32K tokens of context
• Stable: Diffusion V35 Large Turbo: declared precision provider-managed, us, $0.026 per image, 32K tokens of context
• Stable: Image Core: declared precision provider-managed, us, $0.030 per image, 32K tokens of context
• Stable: Image Ultra: declared precision provider-managed, us, $0.080 per image, 32K tokens of context
• Standard: declared precision provider-managed, us, $0.0000040 per character, 4,097 tokens of context
• Starcannon: Unleashed 12B V1.0: declared precision provider-managed, us, $0.494 input and $0.494 output per million tokens, $0.494 cache read per million tokens, 16.4K tokens of context
• Step 3.5 Flash: declared precision provider-managed, us, $0.100 input and $0.300 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
• Step 3.5 Flash 2603: declared precision provider-managed, us, $0.100 input and $0.301 output per million tokens, $0.100 cache read per million tokens, 262.1K tokens of context
• Step 3.7 Flash: declared precision provider-managed, us, $0.200 input and $1.150 output per million tokens, $0.200 cache read per million tokens, 262.1K tokens of context
• Step 3.7 Flash:thinking: declared precision provider-managed, us, $0.200 input and $1.151 output per million tokens, $0.040 cache read per million tokens, 262.1K tokens of context
• Step 5 Preview: declared precision provider-managed, us, $1.001 input and $2.702 output per million tokens, $0.050 cache read per million tokens, 1M tokens of context
• Synth 2.5 Flash: declared precision provider-managed, us, $0.030 input and $0.100 output per million tokens, $0.030 cache read per million tokens, 30K tokens of context
• Synth 2.5 Pro: declared precision provider-managed, us, $0.100 input and $0.200 output per million tokens, $0.100 cache read per million tokens, 30K tokens of context
• Ternary: Bonsai 2 27B: declared precision provider-managed, us, $0.075 input and $0.501 output per million tokens, $0.075 cache read per million tokens, 262.1K tokens of context
• Ternary: Bonsai 2 9B: declared precision provider-managed, us, $0.080 input and $0.130 output per million tokens, $0.040 cache read per million tokens, 262.1K tokens of context
• Text: Embedding 3 Large: declared precision provider-managed, us, $0.130 input per million tokens, 8,000 tokens of context
• Text: Embedding 3 Small: declared precision provider-managed, us, $0.020 input per million tokens, 8,000 tokens of context
• Text: Embedding Ada 002: declared precision provider-managed, us, $0.100 input per million tokens, 8,000 tokens of context
• Text: Embedding V3: declared precision provider-managed, us, $0.070 input per million tokens, 8,192 tokens of context
• Text: Multilingual Embedding 002: declared precision provider-managed, us, $0.025 input per million tokens, 2,000 tokens of context
• Trinity: Large Thinking: declared precision provider-managed, us, $0.250 input and $0.899 output per million tokens, $0.250 cache read per million tokens, 262.1K tokens of context
• Tts 1: declared precision provider-managed, us, $0.000015 per character, 4,097 tokens of context
• Tts 1 1106: declared precision provider-managed, us, $0.000015 per character, 4,097 tokens of context
• Tts 1 Hd: declared precision provider-managed, us, $0.000030 per character, 4,097 tokens of context
• Tts 1 Hd 1106: declared precision provider-managed, us, $0.000030 per character, 4,097 tokens of context
• Unslopnemo 12B V4.1: declared precision provider-managed, us, $0.492 input and $0.492 output per million tokens, $0.492 cache read per million tokens, 8,192 tokens of context
• V1: declared precision provider-managed, us, $0.000047 per second, 1 tokens of context
• Veiled: Calla 12B: declared precision provider-managed, us, $0.300 input and $0.300 output per million tokens, $0.300 cache read per million tokens, 32.8K tokens of context
• Venice Uncensored: declared precision provider-managed, us, $0.400 input and $1.798 output per million tokens, $0.400 cache read per million tokens, 128K tokens of context
• Veo 3.1 Fast: declared precision provider-managed, us, $0.150 per second, 32K tokens of context
• Voxtral: Mini 2602: declared precision provider-managed, us, $0.000050 per second, 1 tokens of context
• Voxtral: Mini Latest: declared precision provider-managed, us, $0.000050 per second, 1 tokens of context
• Voxtral: Mini Transcribe 3.0: declared precision provider-managed, us, $0.000058 per second, 1 tokens of context, the cheapest of 2 offers
• Voxtral: Mini Transcribe Realtime 3: declared precision provider-managed, us, $0.00013 per second, 1 tokens of context
• Voxtral: Mini Transcribe Realtime 3.0: declared precision provider-managed, us, $0.00013 per second, 1 tokens of context
• Voxtral: Mini Tts 2603: declared precision provider-managed, us, $0.000016 per character, 4,097 tokens of context
• Voxtral: Mini Tts 3: declared precision provider-managed, us, $0.000013 per character, 4,097 tokens of context
• Voxtral: Mini Tts 3.0: declared precision provider-managed, us, $0.000013 per character, 4,097 tokens of context
• Voxtral: Mini Tts Latest: declared precision provider-managed, us, $0.000016 per character, 4,097 tokens of context
• Voxtral: Small Transcribe 3.0: declared precision provider-managed, us, $0.000067 per second, 1 tokens of context, the cheapest of 2 offers
• Voyage: Code 2: declared precision provider-managed, us, $0.100 input per million tokens, 4,000 tokens of context
• Voyage: Large 2: declared precision provider-managed, us, $0.120 input per million tokens, 16K tokens of context
• Voyage: Large 2 Instruct: declared precision provider-managed, us, $0.120 input per million tokens, 16K tokens of context
• Wan 2.2 t2i Flash: declared precision provider-managed, us, $0.025 per image, 32K tokens of context
• Wan 2.2 t2i Plus: declared precision provider-managed, us, $0.050 per image, 32K tokens of context
• Wan 2.5 t2i Preview: declared precision provider-managed, us, $0.030 per image, 32K tokens of context
• Wan 2.6 Image: declared precision provider-managed, us, $0.030 per image, 32K tokens of context, the cheapest of 2 offers
• Wan 2.7 Image: declared precision provider-managed, us, $0.030 per image, 32K tokens of context
• Wan 2.7 Image Pro: declared precision provider-managed, us, $0.075 per image, 32K tokens of context, the cheapest of 2 offers
• Wayfarer: Large 70B Llama 3.3: declared precision provider-managed, us, $0.700 input and $0.700 output per million tokens, $0.700 cache read per million tokens, 32.8K tokens of context
• Whisper 1: declared precision provider-managed, us, $0.00017 per second, 1 tokens of context
• Whisper Base: declared precision provider-managed, us, $0.00010 per second, 1 tokens of context, the cheapest of 2 offers
• Whisper Medium: declared precision provider-managed, us, $0.000100 per second, 1 tokens of context, the cheapest of 2 offers
• Whisper Small: declared precision provider-managed, us, $0.000100 per second, 1 tokens of context
• Whisper Tiny: declared precision provider-managed, us, $0.000100 per second, 1 tokens of context
• Whisper: Large V3: declared precision provider-managed, us, $0.0000083 per second, 1 tokens of context, the cheapest of 2 offers
• Wizardlm 2 8x22b: declared precision provider-managed, us, $0.479 input and $0.479 output per million tokens, $0.479 cache read per million tokens, 65.5K tokens of context
• Wizper: declared precision provider-managed, us, $0.00028 per second, 1 tokens of context
• Xing 4.0 29B a4b: declared precision provider-managed, us, $0.220 input and $0.900 output per million tokens, $0.011 cache read per million tokens, 262.1K tokens of context
• Z: Image Base: declared precision provider-managed, us, $0.017 per image, 32K tokens of context
• Z: Image Turbo: declared precision provider-managed, us, $0.012 per image, 32K tokens of context

Related pages

• All providers
• All models
• Discover the best model for your budget
• Quickstart
• llms.txt: the index of every page, as Markdown
• llms-full.txt: every page in one file
• This page as Markdown