Qwen3 235B A22B Thinking 2507
Qwen · Open weights · Released Jul 25, 2025 · qwen/qwen3-235b-a22b-thinking-2507
Best $0.45 in / $3.50 out via Venice · fp8
128K contextToolsReasoningOpen weights
Available from 1 providerUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 9 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.45 | $3.50 | — | 128K | fp8 | 0.92s | 168 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 9 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 1, 2026endpoint removed · cheaperinference2 → 1
Oct 23, 2026endpoint added · cheaperinference1 → 2
Oct 10, 2026endpoint removed · alibaba2 → 1
Oct 10, 2026context changed131072 → 128000
Oct 9, 2026endpoint removed · novita3 → 2
About
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Specifications
Context window128,000
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 25, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-235b-a22b-thinking-2507)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks9 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.