qwen

Qwen: Qwen3 Coder 480B A35B

qwen/qwen3-coder

A coding-focused Qwen candidate for code generation and tool-call evaluation. Its usefulness should be measured by repository tests or another concrete acceptance check.

text

Try in Playground ↗

Input / 1M tokens$0.3

Output / 1M tokens$1

Context window262,144

Maximum output65,536

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pstreamdeveloper_role

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-09-22T08:51:50.371Z · Price version: cmubxr2k207vvjn0zhmrnwsmg:3

Provider pricing fields · USD per indicated unit

{
  "prompt": "0.0000003",
  "completion": "0.000001",
  "input_cache_read": "0.0000001"
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Test empty strings, Unicode and repeated values instead of scoring code by appearance.
The gateway does not execute generated code or tool calls; keep that work in an application sandbox.

Start with the example below, then test representative inputs against your own acceptance criteria.

Make a request

curl --no-buffer https://api.jevrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "qwen/qwen3-coder",
  "messages": [
    {
      "role": "user",
      "content": "Write a JavaScript function that deduplicates strings case-insensitively while preserving the first spelling and order."
    }
  ],
  "max_tokens": 1024
}
JSON

Plan your integration

Connect with the OpenAI Python SDK →Estimate this model’s cost →Budgets, request status and safe retries →

Related models to evaluate

Use identical inputs and scoring rules. No ranking is implied by this selection.

Anthropic: Claude Sonnet 4 OpenAI: GPT-4.1

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.