Alibaba Qwen

Qwen3 Coder 480B

262K ctxText Tools

Released Jul 23, 2025 · 206B tokens this week · 5 providers

Overview

Qwen's flagship coding mixture-of-experts, trained heavily on repository-level tasks and tool use. It handles long files and multi-step edits well and is the most common open-weight substitute for proprietary coding models. Pairs nicely with agentic CLI harnesses.

programmingagentsreasoning

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	262K	66K	$0.30	$1.20	620ms	88	98.70%	fp8
Novita AI	262K	66K	$0.32	$1.30	680ms	74	98.40%	fp8
Together AI	262K	66K	$0.34	$1.34	195ms	120	99.40%	Full
Fireworks AI	262K	66K	$0.35	$1.39	500ms	140	99.50%	Full
Cerebras	131K	66K	$0.36	$1.44	210ms	1300	99.55%	Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

DeepSeek V3.2$0.37

Qwen3 Coder 480B$0.97

Gemini 3 Flash$1.95

GPT-5.2$10.94

Claude Sonnet 4.5$12.00

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder-480b",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'