Qwen3 235B A22B Instruct 2507
- Context
- 262K
- Released
- 1y ago
- Parameters
- 235B
- Input / 1M tokens
- $0.09
- Output / 1M tokens
- $0.55
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Qwen
- Model family
- Qwen
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- July 21, 2025
- Model ID
qwen/qwen3-235b-a22b-2507- Openness
- Open weights
- License
- —
- Parameters
- 235B
- Input modalities
- text
- Output modalities
- text
- Modality
- text->text
- Native context
- 256K
- Tokenizer
- Qwen3
- Max output tokens
- 16K
- Knowledge cutoff
- 2025-06-30
- Hugging Face
- Qwen/Qwen3-235B-A22B-Instruct-2507
- Source freshness
- Endpoints synced Oct 15, 2026, 9:17 AM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| gmicloud/fp8 | 262K | $0.09 | $0.35 | $0.02 | — | 0.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| deepinfra/fp8 | 262K | $0.09 | $0.55 | — | — | 99.31% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| parasail/fp8 | 131K | $0.14 | $0.80 | $0.05 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| venice/fp8 | 128K | $0.15 | $0.75 | — | — | 99.17% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| nebius/fp8 | 262K | $0.20 | $0.60 | — | — | 86.16% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/us-south1 | 262K | $0.25 | $1.00 | — | — | 99.93% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Deployment graph
Can I run this?
Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.