Qwen: Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-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, including instruction following,...
Modalities
In / Out Price
$0.09 / $0.55 per 1M
Context
262K
Released
Jul 21, 2025
Knowledge Cutoff
Jun 2025
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 GMICloudfp8 | 262K | $0.0875 | $0.35 | $0.0175 | — | — | 100.00% |
 DeepInfrafp8 | 262K | $0.09 | $0.55 | — | — | — | 96.67% |
 Parasailfp8 | 131K | $0.14 | $0.80 | $0.05 | — | — | 100.00% |
 Alibaba | 131K | $0.15 | $0.598 | — | — | — | 100.00% |
 Venicefp8 | 128K | $0.15 | $0.75 | — | — | — | 50.00% |
 Nebiusfp8 | 262K | $0.20 | $0.60 | — | — | — | 100.00% |
 StreamLake | 128K | $0.21 | $0.84 | — | — | — | 100.00% |
 Google | 262K | $0.22 | $0.88 | — | — | — | 100.00% |
| Google | 262K | $0.25 | $1 | — | — | — | 100.00% |