# Qwen 3 Coder API

Alibaba's Qwen 3 Coder, 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-coder 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-coder
- Maker: Alibaba
- Context window: 253.8K tokens
- Input price: $0.375 per million tokens
- Output price: $1.250 per million tokens
- Providers: 1 independent provider
- Regions: us

## Providers

- [Pera](https://liquidinference.ai/providers/f651491e-f85b-4f03-b80c-32876aeb80ce.md): us, $0.375 input and $1.250 output per million tokens, $0.375 cache read per million tokens, 253.8K tokens of context

## Scores

- HLE: 3.8, #246 of 273
- GPQA: 51.6, #206 of 250
- AA-LCR: 32.7, #191 of 237
- Terminal-Bench Hard: 15.2, #110 of 166
- LiveCodeBench: 40.3, #68 of 130
- AIME 2025: 29.0, #73 of 100
- MMLU-Pro: 70.6, #90 of 133
- τ²-Bench: 34.5, #127 of 169
- IFBench: 32.7, #154 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

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

## Questions

### What is Qwen 3 Coder?

Qwen 3 Coder is a model from Alibaba.

### How much does Qwen 3 Coder cost?

Offers now ask $0.375 per million input tokens and $1.250 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 Coder?

The largest offer takes 253,808 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.

### What can Qwen 3 Coder do?

Its providers list JSON object, JSON schema, Frequency penalty, Presence penalty, Seed, Stop sequences, Top-p sampling, Text, Tools.

### What inputs and outputs does Qwen 3 Coder support?

Text → Text.

### Which providers serve Qwen 3 Coder?

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 Coder?

Send "qwen3-coder" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.

### When was Qwen 3 Coder listed?

The exchange first listed it on 9/29/2026. This is not its release date.

## Related pages

- [This page in a browser](https://liquidinference.ai/models/qwen3-coder)
- [Qwen 3 14B](https://liquidinference.ai/models/qwen3-14b.md)
- [Qwen 3.8 27B](https://liquidinference.ai/models/qwen3.8-27b.md)
- [Qwen 3 5 4B](https://liquidinference.ai/models/qwen3-5-4b.md)
- [Qwen 3.5 9B](https://liquidinference.ai/models/qwen3.5-9b.md)
- [Qwen 2.5 7B Instruct](https://liquidinference.ai/models/qwen2.5-7b-instruct.md)
- [Qwen 3.6 35B a3b](https://liquidinference.ai/models/qwen3.6-35b-a3b.md)
- [Set up a client](https://liquidinference.ai/connect/qwen3-coder)
- [All models](https://liquidinference.ai/models)
- [Providers](https://liquidinference.ai/providers.md)
- [Discover the best model for your budget](https://liquidinference.ai/discover)
- [Quickstart](https://liquidinference.ai/docs/quickstart.md)
- [llms.txt: the index of every page, as Markdown](https://liquidinference.ai/llms.txt)
- [llms-full.txt: every page in one file](https://liquidinference.ai/llms-full.txt)