Qwen3 235B A22B Instruct 2507
Qwen · Open weights · Released Jul 21, 2025 · qwen/qwen3-235b-a22b-2507
Best $0.087 in / $0.35 out via GMICloud · fp8
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 10 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 5 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 GMICloud | $0.087 | $0.35 | $0.018 | 262K | fp8 | 2s | 46 tok/s | — | 99.9% |
 DeepInfra | $0.09 | $0.55 | — | 262K | fp8 | 0.5s | 30 tok/s | 5/5 | 70.4% |
 Novita | $0.09 | $0.58 | — | 131K | fp8 | ✕ | ✕ | 5/5 | 85.0% |
 Parasail | $0.14 | $0.80 | $0.05 | 131K | fp8 | 1.1s | 54 tok/s | 5/5 | 100.0% |
 Alibaba | $0.149 | $0.598 | — | 131K | — | 1.4s | 37 tok/s | 5/5 | 83.7% |
 Venice | $0.15 | $0.75 | — | 128K | fp8 | ✕ | ✕ | 5/5 | 74.8% |
 Nebius | $0.20 | $0.60 | — | 262K | fp8 | 1.8s | 45 tok/s | 5/5 | 81.5% |
 StreamLake | $0.21 | $0.84 | — | 128K | — | 2.4s | 66 tok/s | — | 99.7% |
 Google | $0.22 | $0.88 | — | 262K | — | 0.87s | 39 tok/s | — | 99.8% |
| Google | $0.25 | $1.00 | — | 262K | — | — | — | — | 99.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · 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 5 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↓ 3% SINCE AUG 23, 2026
$0.09 · AUG 23, 2026$0.087 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.087 / $0.35
per MTok in / out
CACHE READ $0.018
Recent changesRSS ↗
Oct 5, 2026endpoint removed · primeintellect11 → 10
Oct 4, 2026endpoint added · primeintellect10 → 11
Sep 16, 2026endpoint removed · atlascloud11 → 10
Aug 23, 2026price decreased · input0.09 → 0.0875
Aug 23, 2026price decreased · output0.55 → 0.35
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 output16,384
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 API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks19 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.