Qwen3 235B A22B Instruct 2507
by ModelScope · family qwen · listed Apr 2025TW
Qwen instruction model for multilingual chat, reasoning, and tool use
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-235B-A22B-Instruct-2507- Context window
- 262K tokens
- Max output
- 131K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Apr 2025
- Released
- 2025-04-28
- Last updated
- 2025-07-21
- Provider docs
- modelscope.cn/docs/model-service/API-Inference/intro
Back of the envelope
≈
Also listed at
- Cortecs$0.062 in · $0.408 out
- NovitaAI$0.09 in · $0.58 out
- LLM Gateway$0.09 in · $0.58 out
- Meganova$0.09 in · $0.60 out
- Weights & Biases$0.10 in · $0.10 out
- Abacus$0.13 in · $0.60 out
- NanoGPT$0.13 in · $0.50 out
- Venice AI$0.15 in · $0.75 out
- Jiekou.AI$0.15 in · $0.80 out
- submodel$0.20 in · $0.30 out
- Nebius Token Factory$0.20 in · $0.60 out
- Friendli$0.20 in · $0.80 out
- 302.AI$0.29 in · $1.14 out
- Scaleway$0.75 in · $2.25 out
- Qiniu— in · — out