Models / Alibaba / Qwen3 235B-A22B Instruct 2507
Alibaba · qwen
Qwen3 235B-A22B Instruct 2507
Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use
$0.20 in · $0.60 out
per 1M tokens · provider rate closest to the median. No first-party Alibaba price was listed. The reference price is Cortecs's rate, the provider closest to the median.
Provider input prices run from $0.09 to $1.20 per 1M tokens. Output prices run from $0.50 to $3.02.
- Context
- 262,144
- Max output
- 16,384
- Cache read
- $0.018
- Cache write
- —
- Reasoning
- No
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- No
- Open weights
- Yes
- License
- Apache 2.0
- Released
- Jul 21, 2025
- Updated in source
- Jul 21, 2025
- Knowledge
- —
- Providers
- 11
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Deep Infra | $0.09 | $0.55 | — | — | — |
| LLM Gateway | $0.09 | $0.58 | — | — | — |
| Merge Gateway | $0.10 | $0.60 | $0.057 | — | — |
| NanoGPT | $0.13 | $0.50 | $0.065 | — | — |
| Venice AI | $0.15 | $0.75 | — | — | — |
| Cortecsreference | $0.20 | $0.60 | $0.018 | — | — |
| Amazon Bedrock | $0.22 | $0.88 | — | — | — |
| Crusoe | $0.22 | $0.80 | $0.11 | — | — |
| Hugging Face | $0.86 | $2.57 | — | — | — |
| Eden AI | $1.01 | $3.02 | — | — | — |
| Pioneer | $1.20 | $1.20 | $1.20 | $1.20 | — |
Jobs this model qualifies for
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar