Qwen3 235B A22B Instruct 2507
Qwen · Open weights · Released Jul 21, 2025 · qwen/qwen3-235b-a22b-2507
Best $0.09 in / $0.55 out via DeepInfra · fp8
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · PRICES 16 MINUTES AGO · SPEED 24 HOURS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.072 | $0.44 | — | 262K | fp8 | — | — | 5/5 | 100.0% | |
| $0.09 | $0.55 | — | 262K | fp8 | 1.2s | 32 tok/s | — | 96.4% | |
| $0.135 | $0.825 | — | 262K | fp8 | — | — | — | 96.5% | |
| $0.14 | $0.80 | $0.05 | 131K | fp8 | 1.1s | 40 tok/s | 5/5 | 100.0% | |
| $0.15 | $0.75 | — | 128K | fp8 | 0.95s | 25 tok/s | 5/5 | 99.1% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 24 hours ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 19, 2026endpoint removed · nebius6 → 5
Nov 11, 2026endpoint added · nebius4 → 4
Nov 11, 2026endpoint removed · gmicloud4 → 4
Nov 1, 2026endpoint removed · cheaperinference5 → 4
Oct 29, 2026endpoint removed · google7 → 5
Oct 28, 2026endpoint added · cheaperinference6 → 7
Oct 27, 2026endpoint removed · cheaperinference7 → 6
Oct 23, 2026endpoint added · cheaperinference6 → 7
About
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, including instruction following,...
Specifications
Context window262,144
Max output117,964
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 21, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-235b-a22b-2507)Sources
OpenRouter API16 minutes ago
AGGREGATORHugging Face16 minutes ago
COMMUNITYModelIndex benchmarks9 days ago
MEASUREDVerified 16 minutes ago · list prices, not negotiated rates.