Qwen / qwen/qwen3-vl-235b-a22b-instruct
Qwen3-VL-235B-A22B-Instruct - access through LLMTR
Qwen3-VL-235B-A22B-Instruct is the largest open-weight vision-language model in the Qwen3-VL line, a Mixture-of-Experts model that runs 22 billion of its 235 billion parameters per token. It reads text and images together and suits document and screenshot reading, OCR, chart and table interpretation, and visual question answering. It answers directly, without a reasoning step. The 262,144-token context window is shared between input and output. It supports tool calling, JSON mode and JSON Schema structured output, accepts text and image input (base64 or an https link), and produces text.
Technical specifications
| Canonical ID | qwen/qwen3-vl-235b-a22b-instruct |
|---|---|
| Provider | Qwen |
| Context window | 262,144 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.200000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.110000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.880000 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"qwen/qwen3-vl-235b-a22b-instruct","messages":[{"role":"user","content":"Hello"}]}'Related models
- Qwen3.8-Max qwen/qwen3.8-max
- Qwen3.7-Max qwen/qwen3.7-max
- Qwen3.7-Plus qwen/qwen3.7-plus
- Qwen3.8-Flash qwen/qwen3.8-flash
- Qwen3.6-Flash qwen/qwen3.6-flash
- Qwen-Plus qwen/qwen-plus
- Qwen-Plus-2025-01-25 qwen/qwen-plus-2025-01-25
- Qwen-Plus-2025-04-28 qwen/qwen-plus-2025-04-28