Qwen3 VL 235B A22B Instruct
by Prime Inference · family qwen · listed Sep 2025TVW
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.30
Output$1.50
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen/qwen3-vl-235b-a22b-instruct- Context window
- 262K tokens
- Max output
- 33K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Mar 2025
- Released
- 2025-09-23
- Last updated
- 2025-09-23
- Provider docs
- docs.primeintellect.ai/inference/overview
Back of the envelope
≈
Also listed at
- Deep Infra$0.20 in · $0.88 out
- LLM Gateway$0.20 in · $0.88 out
- Eden AI$0.20 in · $0.88 out
- DevPass (LLM Gateway)$0.20 in · $0.88 out
- Kilo Gateway$0.21 in · $1.90 out
- OpenRouter$0.21 in · $1.90 out
- Merge Gateway$0.287 in · $1.15 out
- NanoGPT$0.30 in · $1.90 out
- Hugging Face$0.30 in · $1.50 out
- Jalapeno Cloud$0.30 in · $1.50 out
- Helicone$0.30 in · $1.50 out
- OrcaRouter$0.40 in · $1.60 out