Qwen 3 8B API

Alibaba's Qwen 3 8B, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send qwen3-8b as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: qwen3-8b
Maker: Alibaba
Context window: 32.8K tokens
Input price: $0.092 per million tokens
Output price: $0.287 per million tokens
Providers: 1 independent provider
Regions: eu-central

Providers

Greenference: eu-central, $0.092 input and $0.287 output per million tokens, $0.046 cache read per million tokens, 32.8K tokens of context

Scores

HLE: 1.9, #272 of 273
GPQA: 45.2, #221 of 250
AA-LCR: 0.0, #231 of 237
Terminal-Bench Hard: 2.3, #154 of 166
LiveCodeBench: 20.2, #109 of 130
AIME 2025: 24.3, #80 of 100
MMLU-Pro: 64.3, #107 of 133
τ²-Bench: 24.9, #144 of 169
IFBench: 28.6, #165 of 178
SimpleQA Verified: 20.3, #93 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-8b",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Qwen 3 8B?: Qwen 3 8B is a model from Alibaba.
How much does Qwen 3 8B cost?: Offers now ask $0.092 per million input tokens and $0.287 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Qwen 3 8B?: The largest offer takes 32,768 input tokens. One job can generate up to 32,768 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Qwen 3 8B do?: Its providers list Frequency penalty, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text.
What inputs and outputs does Qwen 3 8B support?: Text → Text.
Which providers serve Qwen 3 8B?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Qwen 3 8B?: Send "qwen3-8b" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Qwen 3 8B listed?: The exchange first listed it on 10/14/2026. This is not its release date.