Pera

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

Facts

Handle

pera

Website

https://primaera.xyz/

On the exchange since

2026-10-10

Models

35

Offers

36

Regions

asia, us

Precisions (declared)

bf16, fp4, fp8, mxfp4, provider-managed

Lowest price on

27 of 35 models

Reliability, last 3 days

Probes answered

99.32%

Hours with an answer

100.0%

Median response time

2.8s

Checked by the exchange

14 of 36 offers match the fingerprint of the model. 1 has 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, declared by the provider
• No training, declared by the provider

Models

• DeepSeek V3.2: declared precision fp4, us, $0.325 input and $0.475 output per million tokens, $0.325 cache read per million tokens, 160K tokens of context
• DeepSeek V4 Flash: declared precision fp8, us, $0.140 input and $0.280 output per million tokens, $0.140 cache read per million tokens, $0.00057 fee for each request, 1M tokens of context
• DeepSeek V4 Flash 0731: declared precision fp8, us, $0.038 input and $0.0018 output per million tokens, $0.038 cache read per million tokens, 1M tokens of context
• DeepSeek V4 Pro: declared precision fp8, us, $2.475 input and $3.005 output per million tokens, $2.475 cache read per million tokens, $0.0025 fee for each request, 1M tokens of context
• DeepSeek V4.1 Flash: declared precision fp8, us, $0.140 input and $0.0084 output per million tokens, $0.140 cache read per million tokens, $0.000058 fee for each request, 1M tokens of context
• DeepSeek V4.1 Flash 1017:thinking: declared precision fp8, us, $0.392 input and $0.012 output per million tokens, $0.392 cache read per million tokens, $0.018 fee for each request, 1M tokens of context
• DeepSeek V4.1 Flash:thinking: declared precision fp8, us, $0.405 input and $0.0099 output per million tokens, $0.405 cache read per million tokens, $0.0043 fee for each request, 1M tokens of context
• Gemma 3 27B It: declared precision fp8, us, $0.100 input and $0.200 output per million tokens, $0.100 cache read per million tokens, 40K tokens of context
• GLM 4.7: declared precision fp4, us, $0.750 input and $2.750 output per million tokens, $0.750 cache read per million tokens, 128K tokens of context
• GLM 5.2: declared precision fp4, us, $0.563 input and $1.800 output per million tokens, $0.563 cache read per million tokens, $0.02 fee for each request, 1M tokens of context
• GLM 5.3: declared precision fp4, us, $0.285 input and $2.825 output per million tokens, $0.285 cache read per million tokens, $0.02 fee for each request, 1M tokens of context
• GLM 5.3 Flash: declared precision fp4, us, $0.150 input and $0.137 output per million tokens, $0.150 cache read per million tokens, $0.00065 fee for each request, 1M tokens of context
• GPT 5.6 Sol: declared precision provider-managed, us, $5.000 input and $37.500 output per million tokens, $5.000 cache read per million tokens, 1M tokens of context
• GPT 6 Astra: declared precision provider-managed, us, $30.000 input and $112.500 output per million tokens, $30.000 cache read per million tokens, $0.02 fee for each request, 1M tokens of context
• GPT 6 Luna: declared precision provider-managed, us, $0.125 input and $0.938 output per million tokens, $0.125 cache read per million tokens, 1M tokens of context
• GPT 6 Sol: declared precision provider-managed, us, $2.500 input and $18.750 output per million tokens, $2.500 cache read per million tokens, 1M tokens of context
• GPT 6.1 Sol: declared precision provider-managed, us, $2.910 input and $7.104 output per million tokens, $2.910 cache read per million tokens, $0.02 fee for each request, 1M tokens of context
• GPT: OSS 120B: declared precision bf16, us, $0.037 input and $0.0034 output per million tokens, $0.037 cache read per million tokens, $0.00017 fee for each request, 122.9K tokens of context
• GPT: OSS 20B: declared precision bf16, us, $0.037 input and $0.175 output per million tokens, $0.037 cache read per million tokens, 122.9K tokens of context
• hy4 Preview: declared precision fp8, us, $1.042 input and $3.126 output per million tokens, $1.042 cache read per million tokens, 991.8K tokens of context
• Kimi K3: declared precision mxfp4, asia, $1.800 input and $0.100 output per million tokens, $0.180 cache read per million tokens, $0.00025 fee for each request, 1M tokens of context, the cheapest of 2 offers
• Kimi K3.1 Pro: declared precision provider-managed, us, $4.000 input and $20.000 output per million tokens, $4.000 cache read per million tokens, $0.02 fee for each request, 1M tokens of context
• Mimo V2.6 Flash: declared precision fp8, us, $0.105 input and $0.0056 output per million tokens, $0.105 cache read per million tokens, $0.002 fee for each request, 1M tokens of context
• Mimo V2.6 Pro: declared precision fp8, us, $0.652 input and $1.305 output per million tokens, $0.652 cache read per million tokens, $0.00046 fee for each request, 1M tokens of context
• MiniMax M3: declared precision fp8, us, $0.350 input and $1.375 output per million tokens, $0.350 cache read per million tokens, 516.1K tokens of context
• Mistral: Small 3.2 24B Instruct: declared precision fp8, us, $0.100 input and $0.0040 output per million tokens, $0.100 cache read per million tokens, $0.000049 fee for each request, 128K tokens of context
• Nemotron 3 Super 120B a12b: declared precision bf16, us, $0.120 input and $0.346 output per million tokens, $0.120 cache read per million tokens, $0.00052 fee for each request, 254K tokens of context
• Nemotron 3 Ultra 550B a55b: declared precision fp4, us, $0.450 input and $0.044 output per million tokens, $0.450 cache read per million tokens, $0.00057 fee for each request, 262.1K tokens of context
• Nemotron 3.5 Lightning: declared precision bf16, us, $0.053 input and $0.017 output per million tokens, $0.053 cache read per million tokens, $0.000072 fee for each request, 262.1K tokens of context
• Qwen 3 14B: declared precision fp8, us, $0.087 input and $0.0048 output per million tokens, $0.087 cache read per million tokens, $0.000079 fee for each request, 32.8K tokens of context
• Qwen 3 Coder: declared precision fp4, us, $0.375 input and $1.250 output per million tokens, $0.375 cache read per million tokens, 253.8K tokens of context
• Qwen 3 VL 235B a22b Instruct: declared precision fp8, us, $0.250 input and $1.100 output per million tokens, $0.250 cache read per million tokens, 256K tokens of context
• Qwen 3.5 397B a17b: declared precision fp8, us, $0.500 input and $3.600 output per million tokens, $0.500 cache read per million tokens, $0.00048 fee for each request, 128K tokens of context
• Qwen 3.6 35B a3b: declared precision fp8, us, $0.150 input and $0.125 output per million tokens, $0.150 cache read per million tokens, $0.00083 fee for each request, 262.1K tokens of context
• Qwen 3.8 27B: declared precision bf16, us, $0.045 input and $0.013 output per million tokens, $0.045 cache read per million tokens, $0.000097 fee for each request, 262.1K 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