Qwen3 235B A22B Instruct 2507 FP8 Throughput
235B MoE model with 22B activation featuring enhanced instruction following, reasoning, and 262K context for cost-efficient high-throughput inference.

About model
Enhanced Qwen3 model optimized for serverless inference with superior price-performance.
Model | FrontierMath Tier 4 | GPQA Diamond | HLE | SciCode | GDPval-AA | Terminal-Bench 2.1 | Agent Arena | FrontierCode | DeepSWE |
|---|---|---|---|---|---|---|---|---|---|
Qwen3 235B A22B Instruct 2507 FP8 Throughput | 65.9% | Related open-source models | Competitor closed-source models | ||||||
87.8% | 92.6% | 53% | 60% | 62% | 85% | 53.5% | 70% | ||
73.2% | 93.2% | 53% | 56% | 68% | 89% | +16.4pp | 53.4% | 74% | |
82.9% | 94.1% | 47% | 56% | 61% | 88% | 47.5% | 73% | ||
24.4% | 93.1% | 40% | 54% | 51% | 82% | +4.2pp | 42.4% | 54% | |
61.0% | 91.1% | 37% | 53% | 54% | 81% | 39.8% | 67% |
API usage
Endpoint:
- TypeChatReasoning
- Main use casesChatSmall & FastMedium General PurposeFunction Calling
- FeaturesFunction CallingJSON Mode
- DeploymentDedicatedServerless
- Parameters235B
- Context length262K
- Input price
$0.20 / 1M tokens
- Output price
$0.60 / 1M tokens
- Input modalitiesText
- Output modalitiesText
- ReleasedJuly 22, 2025
- Quantization levelFP8
- External link
- CategoryChat
