Alibaba Qwen

Qwen3 235B A22B

262K ctxText Tools Reasoning

Released Apr 29, 2025 · 118B tokens this week · 5 providers

Overview

A large mixture-of-experts with only about 22B active parameters per token, so it serves far more cheaply than its size suggests. Supports switchable thinking and non-thinking modes in one checkpoint. A strong open-weight generalist.

reasoningprogrammingtranslation

Providers

Reference data — not yet measured from live traffic

PROVIDER		MAX OUT		OUTPUT /M				QUANT
DeepInfraCheapest	262K	33K	$0.13	$0.60	540ms	105	98.80%	fp8
Novita AI	262K	33K	$0.14	$0.64	600ms	90	98.50%	fp8
Together AI	262K	33K	$0.15	$0.67	195ms	135	99.40%	Full
Fireworks AI	262K	33K	$0.15	$0.69	460ms	150	99.50%	Full
Cerebras	131K	33K	$0.16	$0.72	200ms	1400	99.60%	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 235B A22B$0.48

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/qwen3-235b-a22b",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'