EmpirioLabs AI

Text, image, speech and video models: open models EmpirioLabs AI runs on GPU infrastructure it manages, plus proprietary partner models.

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

Facts

Handle: empiriolabs
Website: https://empiriolabs.ai/
Terms of service: https://empiriolabs.ai/policy/terms-of-service
Privacy policy: https://empiriolabs.ai/policy/privacy-policy
Status page: https://status.empiriolabs.ai/
On the exchange since: 2026-10-16
Models: 103
Offers: 132
Regions: global
Precisions (declared): bf16, fp16, fp4, fp8, int2, int8, mixed, provider-managed
Lowest price on: 44 of 59 models

Reliability, last 3 days

Probes answered: 99.09%
Hours with an answer: 100.0%
Median response time: 2.8s

Checked by the exchange

3 of 132 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, in review
No training, in review
GDPR DPA, in review
CSA STAR, in review

Models

Aplomb 1: declared precision bf16, global, $0.020 input and Free output per million tokens, $0.020 cache read per million tokens, 1M tokens of context
Aplomb 1 Decision: declared precision bf16, global, $0.020 input and — output per million tokens, 1M tokens of context
DeepSeek V4 Flash 0731: declared precision provider-managed, global, $0.424 input and $1.272 output per million tokens, $0.424 cache read per million tokens, 1M tokens of context
DeepSeek V4 Pro: declared precision provider-managed, global, $1.650 input and $3.300 output per million tokens, $1.650 cache read per million tokens, 1M tokens of context
DeepSeek V4 Pro 0813: declared precision provider-managed, global, $1.320 input and $3.960 output per million tokens, $1.320 cache read per million tokens, 1M tokens of context
DeepSeek V4.1 Flash 1017: declared precision provider-managed, global, $0.200 input and $0.800 output per million tokens, $0.020 cache read per million tokens, 1M tokens of context
Flux 2 Klein 4B: declared precision bf16, global, $0.0085 per image, 512 tokens of context
Gemma 4 26B a4b It: declared precision fp8, global, $0.050 input and $0.290 output per million tokens, $0.025 cache read per million tokens, 262.1K tokens of context
GLM 4 6v Flashx: declared precision provider-managed, global, $0.040 input and $0.400 output per million tokens, $0.036 cache read per million tokens, 131.1K tokens of context
GLM 4.7 Flashx: declared precision provider-managed, global, $0.070 input and $0.400 output per million tokens, $0.063 cache read per million tokens, 202.8K tokens of context
GLM 5.1: declared precision provider-managed, global, $0.825 input and $3.301 output per million tokens, $0.165 cache read per million tokens, 8,000 tokens of context
GLM 5.2: declared precision provider-managed, global, $1.400 input and $4.400 output per million tokens, $1.400 cache read per million tokens, 1M tokens of context
GLM 5.3: declared precision provider-managed, global, $1.400 input and $4.400 output per million tokens, $1.400 cache read per million tokens, 1M tokens of context
GLM 5.3 Flash: declared precision provider-managed, global, $0.075 input and $0.250 output per million tokens, $0.075 cache read per million tokens, 1M tokens of context
GLM Tts: declared precision int8, global, $0.00020 per character, 8,192 tokens of context, the cheapest of 2 offers
GPT: Image 2: declared precision provider-managed, global, $0.012 per image, 1,024 tokens of context
Grok: Imagine Image 2 0: declared precision provider-managed, global, $0.048 per image, 1,024 tokens of context
Grok: Imagine Video 1 5: declared precision provider-managed, global, $0.096 per second, 1,024 tokens of context, the cheapest of 3 offers
Happyhorse 1 0: declared precision provider-managed, global, $0.140 per second, 1,024 tokens of context, the cheapest of 2 offers
Happyhorse 1 1: declared precision provider-managed, global, $0.140 per second, 1,024 tokens of context, the cheapest of 2 offers
Hunyuan: Image 3: declared precision provider-managed, global, $0.130 per image, 1,024 tokens of context
Hunyuan: Video 1 5: declared precision mixed, global, $0.061 per second, 1,024 tokens of context, the cheapest of 3 offers
Kimi K2.6: declared precision provider-managed, global, $0.894 input and $3.713 output per million tokens, $0.179 cache read per million tokens, 262.1K tokens of context
Kimi K2.7 Code: declared precision provider-managed, global, $0.950 input and $4.000 output per million tokens, $0.950 cache read per million tokens, 262.1K tokens of context
Kimi K2.7 Code Highspeed: declared precision provider-managed, global, $1.900 input and $8.000 output per million tokens, $1.900 cache read per million tokens, 262.1K tokens of context
Kimi K3: declared precision provider-managed, global, $3.000 input and $15.000 output per million tokens, $3.000 cache read per million tokens, 1M tokens of context
Kimi K3.1 Pro: declared precision provider-managed, global, $2.000 input and $10.000 output per million tokens, $0.184 cache read per million tokens, 1M tokens of context
Kling 3 0 Turbo: declared precision provider-managed, global, $0.180 per second, 1,024 tokens of context
Mimo V2.6 Flash: declared precision provider-managed, global, $0.140 input and $0.280 output per million tokens, $0.140 cache read per million tokens, 1M tokens of context
Mimo V2.6 Pro: declared precision provider-managed, global, $0.435 input and $0.870 output per million tokens, $0.435 cache read per million tokens, 1M tokens of context
Mimo V2.6 Pro Ultraspeed: declared precision provider-managed, global, $4.350 input and $8.700 output per million tokens, $4.350 cache read per million tokens, 1M tokens of context
Mistral: Small 4 119B 2603: declared precision provider-managed, global, $0.150 input and $0.600 output per million tokens, $0.150 cache read per million tokens, 262.1K tokens of context
Moss: Image Turbo: declared precision int8, global, $0.015 per image, 1,024 tokens of context
Moss: Video And Audio: declared precision bf16, global, $0.120 per second, $0.065 fee for each request, 1,024 tokens of context
Muse: Glimmer 30B: declared precision fp4, global, $0.200 input and $0.800 output per million tokens, $0.050 cache read per million tokens, 131.1K tokens of context
Muse: Spark 1.1: declared precision provider-managed, global, $1.250 input and $4.250 output per million tokens, $1.000 cache read per million tokens, 1M tokens of context
Muse: Spark 1.2: declared precision provider-managed, global, $1.250 input and $4.250 output per million tokens, $1.000 cache read per million tokens, 1M tokens of context
Muse: Spark 1.3: declared precision provider-managed, global, $1.250 input and $4.250 output per million tokens, $1.000 cache read per million tokens, 1M tokens of context
Nova 2 Lite V1: declared precision provider-managed, global, $0.380 input and $3.160 output per million tokens, $0.213 cache read per million tokens, 1M tokens of context
Nova: Lite 1 0: declared precision provider-managed, global, $0.069 input and $0.280 output per million tokens, $0.039 cache read per million tokens, 317.4K tokens of context
Nova: Micro 1 0: declared precision provider-managed, global, $0.040 input and $0.160 output per million tokens, $0.022 cache read per million tokens, 133K tokens of context
Nova: Pro 1 0: declared precision provider-managed, global, $2.400 input and $9.600 output per million tokens, $2.400 cache read per million tokens, 317.3K tokens of context
Perplexity Sonar: declared precision provider-managed, global, $2.400 input and $2.400 output per million tokens, $2.400 cache read per million tokens, $0.019 fee for each request, 919.3K tokens of context
Perplexity: Sonar Pro: declared precision provider-managed, global, $7.200 input and $36.000 output per million tokens, $7.200 cache read per million tokens, $0.024 fee for each request, 919.3K tokens of context
Perplexity: Sonar Reasoning Pro: declared precision provider-managed, global, $4.800 input and $19.000 output per million tokens, $4.800 cache read per million tokens, $0.024 fee for each request, 919.3K tokens of context
Pixverse C1: declared precision provider-managed, global, $0.031 per second, 1,024 tokens of context, the cheapest of 4 offers
Pixverse V6: declared precision provider-managed, global, $0.026 per second, 1,024 tokens of context, the cheapest of 4 offers
Pixverse V6 Max: declared precision provider-managed, global, $0.031 per second, 1,024 tokens of context, the cheapest of 4 offers
Qwen 3 5 4B: declared precision fp8, global, $0.040 input and $0.070 output per million tokens, $0.020 cache read per million tokens, 262.1K tokens of context
Qwen 3 5 Omni Flash: declared precision provider-managed, global, $0.800 input and $4.400 output per million tokens, $0.800 cache read per million tokens, 196.6K tokens of context
Qwen 3 5 Omni Plus: declared precision provider-managed, global, $2.800 input and $16.600 output per million tokens, $2.800 cache read per million tokens, 196.6K tokens of context
Qwen 3.5 122B a10b: declared precision provider-managed, global, $0.115 input and $0.917 output per million tokens, $0.115 cache read per million tokens, 32K tokens of context
Qwen 3.5 27B: declared precision provider-managed, global, $0.086 input and $0.688 output per million tokens, $0.086 cache read per million tokens, 32K tokens of context
Qwen 3.5 35B a3b: declared precision provider-managed, global, $0.057 input and $0.459 output per million tokens, $0.057 cache read per million tokens, 32K tokens of context
Qwen 3.5 397B a17b: declared precision provider-managed, global, $0.172 input and $1.032 output per million tokens, $0.172 cache read per million tokens, 32K tokens of context
Qwen 3.5 9B: declared precision fp8, global, $0.090 input and $0.130 output per million tokens, $0.045 cache read per million tokens, 262.1K tokens of context
Qwen 3.5 Flash: declared precision provider-managed, global, $0.090 input and $0.368 output per million tokens, $0.090 cache read per million tokens, 995.9K tokens of context
Qwen 3.5 Plus: declared precision provider-managed, global, $0.360 input and $2.210 output per million tokens, $0.360 cache read per million tokens, 64K tokens of context
Qwen 3.6 27B: declared precision provider-managed, global, $0.413 input and $2.475 output per million tokens, $0.413 cache read per million tokens, 229.4K tokens of context
Qwen 3.6 35B a3b: declared precision int2, global, $0.070 input and $0.420 output per million tokens, $0.035 cache read per million tokens, 131.1K tokens of context
Qwen 3.6 Flash: declared precision provider-managed, global, $0.250 input and $1.500 output per million tokens, $0.250 cache read per million tokens, 64K tokens of context
Qwen 3.6 Plus: declared precision provider-managed, global, $0.500 input and $3.000 output per million tokens, $0.500 cache read per million tokens, 64K tokens of context
Qwen 3.7 Flash: declared precision provider-managed, global, $0.030 input and $0.130 output per million tokens, $0.0060 cache read per million tokens, 8,000 tokens of context
Qwen 3.7 Max: declared precision provider-managed, global, $2.500 input and $7.500 output per million tokens, $2.500 cache read per million tokens, 983.6K tokens of context
Qwen 3.7 Plus: declared precision provider-managed, global, $0.400 input and $1.600 output per million tokens, $0.400 cache read per million tokens, 64K tokens of context
Qwen 3.8 27B: declared precision fp4, global, $0.170 input and $0.500 output per million tokens, $0.080 cache read per million tokens, 262.1K tokens of context
Qwen 3.8 Flash: declared precision provider-managed, global, $0.160 input and $0.470 output per million tokens, $0.160 cache read per million tokens, 983.6K tokens of context
Qwen 3.8 Max: declared precision provider-managed, global, $2.000 input and $6.000 output per million tokens, $2.000 cache read per million tokens, 983.6K tokens of context
Qwen 3.8 Max 0902: declared precision provider-managed, global, $2.000 input and $6.000 output per million tokens, $2.000 cache read per million tokens, 983.6K tokens of context
Qwen 3.8 Omni Flash: declared precision provider-managed, global, $0.300 input and $0.940 output per million tokens, $0.300 cache read per million tokens, 1M tokens of context
Qwen: Audio 3 0 Asr: declared precision provider-managed, global, $0.000070 per second, 8,192 tokens of context
Qwen: Audio 3 0 Tts: declared precision provider-managed, global, $0.000015 per character, 8,192 tokens of context, the cheapest of 2 offers
Qwen: Audio 3 1 Tts Plus: declared precision provider-managed, global, $0.000060 per character, 8,192 tokens of context
Qwen: Image 2 1: declared precision provider-managed, global, $0.040 per image, 1,024 tokens of context
Qwen: Image 2.0: declared precision provider-managed, global, $0.075 per image, 1,024 tokens of context
Qwen: Image 3 0: declared precision provider-managed, global, $0.075 per image, 1,024 tokens of context
Seed 2.0 Code: declared precision provider-managed, global, $0.400 input and $2.400 output per million tokens, $0.400 cache read per million tokens, 32K tokens of context
Seed 2.0 Lite: declared precision provider-managed, global, $0.310 input and $2.500 output per million tokens, $0.310 cache read per million tokens, 32K tokens of context
Seed 2.0 Mini: declared precision provider-managed, global, $0.120 input and $0.500 output per million tokens, $0.120 cache read per million tokens, 32K tokens of context
Seed 2.0 Pro: declared precision provider-managed, global, $0.630 input and $3.790 output per million tokens, $0.630 cache read per million tokens, 32K tokens of context
Seed 2.1 Turbo: declared precision provider-managed, global, $0.630 input and $3.130 output per million tokens, $0.630 cache read per million tokens, 229.1K tokens of context
Seedance 1 5 Pro: declared precision provider-managed, global, $0.048 per second, 1,024 tokens of context, the cheapest of 3 offers
Seedance 2 0 Fast: declared precision provider-managed, global, $0.122 per second, 1,024 tokens of context, the cheapest of 2 offers
Seedance 2 0 Mini: declared precision provider-managed, global, $0.070 per second, 1,024 tokens of context, the cheapest of 2 offers
Seedance 2 0 Pro: declared precision provider-managed, global, $0.139 per second, 1,024 tokens of context, the cheapest of 3 offers
Seedance 2 5: declared precision provider-managed, global, $0.206 per second, 1,024 tokens of context, the cheapest of 3 offers
Seedream 4 0: declared precision provider-managed, global, $0.060 per image, 1,024 tokens of context
Seedream 4.5: declared precision provider-managed, global, $0.080 per image, 1,024 tokens of context
Seedream 5 0 Flash: declared precision provider-managed, global, $0.030 per image, 1,024 tokens of context
Seedream 5.0 Lite Preview: declared precision provider-managed, global, $0.035 per image, 1,024 tokens of context
Skylark: Embedding Vision: declared precision provider-managed, global, $0.250 input per million tokens, 8,000 tokens of context
Soulx Podcast: declared precision bf16, global, $0.000015 per character, 8,192 tokens of context, the cheapest of 2 offers
Svi 2 0 Pro: declared precision mixed, global, $0.057 per second, $0.065 fee for each request, 1,024 tokens of context
Text: Embedding V4: declared precision provider-managed, global, $0.070 input per million tokens, 8,192 tokens of context
Tongyi: Embedding Vision Flash: declared precision provider-managed, global, $0.090 input per million tokens, 1,024 tokens of context
Tongyi: Embedding Vision Plus: declared precision provider-managed, global, $0.090 input per million tokens, 1,024 tokens of context
Wan 2 1 Image: declared precision provider-managed, global, $0.025 per image, 1,024 tokens of context
Wan 2 2 Image: declared precision provider-managed, global, $0.050 per image, 1,024 tokens of context
Wan 2 5: declared precision provider-managed, global, $0.050 per second, 1,024 tokens of context, the cheapest of 3 offers
Wan 2 5 Image: declared precision provider-managed, global, $0.030 per image, 1,024 tokens of context
Wan 2 6: declared precision provider-managed, global, $0.050 per second, 1,024 tokens of context, the cheapest of 2 offers
Wan 2.7 Image: declared precision provider-managed, global, $0.075 per image, 1,024 tokens of context
Whisper: Large V3 Turbo: declared precision fp16, global, $0.000083 per second, 8,192 tokens of context