QQwen · Released Jul 21, 2025
Qwen3 235B A22B Instruct 2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation…
- Top 30%Lech Mazur Writing
- Top 43%Aider Polyglot
- Released
- Jul 21 2025
- Context window
- 262K 16K out
- Input / 1M tokens
- $0.09 from $0.072
- Output / 1M tokens
- $0.55 from $0.35
Where to run it
8 providers compared
Cheapest: GMICloud at $0.088 / $0.35 per 1M input / output tokens — 60% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| GMICloudFP8 | $0.088 | $0.35 | $0.018 | 262K | 236K | 0%24h | Cheapest |
| TensorX | $0.072 | $0.46 | $0.018 | 131K | 262K | — | +11% |
| DeepInfraFP8 | $0.09 | $0.55 | — | 262K | 16K | 81.8%24h | +34% |
| Kilo Gateway | $0.09 | $0.55 | — | 262K | 16K | — | +34% |
| VeniceFP8 | $0.15 | $0.75 | — | 128K | 16K | 91.9%24h | +95% |
| NebiusFP8 | $0.20 | $0.60 | — | 262K | 236K | 42.1%24h | +95% |
| ParasailFP8 | $0.14 | $0.80 | $0.05 | 131K | 118K | 100%24h | +99% |
| Googleus-south1 | $0.22 | $0.88 | — | 262K | 16K | 37.7%24h | +151% |
Value
Price vs. performance
Qwen3 235B A22B Instruct 2507 Other Qwen Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
6 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Aider PolyglotSoftware engineering · Hard Exercism problems in many languages | 59.6% | #11of 26 | GPT-588.0% |
| Lech Mazur WritingWriting & content · Short stories weaving 10 required elements, judged 0–10 | 8.30/10 | #8of 27 | GPT-58.60/10 |
| Fiction.LiveBenchWriting & content · Understanding long creative writing (16k tokens) | 67.7% | #13of 24 | GPT-597.2% |
| GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions | 70.7% | #86of 122 | Gemini 4 Argon96.4% |
| SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people | 31.0% | #44of 58 | Claude Fable 581.9% |
| LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts | 25.0% | #88of 123 | Claude Sonnet 5.568.3% |
Specs
Details
- Model ID
qwen/qwen3-235b-a22b-2507- Developer
- Qwen
- Release date
- Jul 21, 2025 ·
- Context window
- 262,144 tokens
- Max output
- 16,384 tokens
- API price
- $0.09 / $0.55 per 1M input / output tokens
- Providers
- 8
- Input types
- text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.