← Model list
Qwen3 VL 235B A22B Thinking
alibaba·alibaba/qwen3-vl-235b-a22b-thinking·GA·Open weights·qwen series
Qwen vision-language thinking model for visual reasoning, documents, and agent tasks
At a glance
Reference price$0.50 / $6.00 per 1M
Cache read $0.25 · NanoGPT
Lowest paid$0.287 / $2.87
Merge Gateway Gateway · 3.4× spread
Context32,768
⚠ Providers report 32,768–131,072; the table below is authoritative
Output limit32,768
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Knowledge cutoff2025-03-31
Released / updated2025-09-23 / 2025-09-23
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 9 providers9 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Merge Gateway | Gateway | $0.287 | $2.87 | $0.057 | — | 131,072 ⚠ | 32,768 | |
| OpenRouter | Gateway | $0.40 | $4.00 | — | — | 131,072 ⚠ | 32,768 | |
| Eden AI | Gateway | $0.40 | $4.00 | — | — | 131,072 ⚠ | 32,768 | |
| Kilo Gateway | Gateway | $0.40 | $4.00 | — | — | 131,072 ⚠ | 32,768 | |
| Jalapeno Cloud Qwen3-VL-235B-A22B-Thinking | Gateway | $0.98 | $3.95 | — | — | 131,072 ⚠ | 32,768 | |
| Hugging Face Qwen/Qwen3-VL-235B-A22B-Thinking | Cloud | $0.98 | $3.95 | — | — | 131,072 ⚠ | 32,768 | |
| NovitaAI | Gateway | $0.98 | $3.95 | — | — | 131,072 ⚠ | 32,768 | |
| DevPass (LLM Gateway) | Gateway | $0.98 | $3.95 | — | — | 131,072 ⚠ | 8,192 | |
| NanoGPT | Gateway | $0.50 | $6.00 | $0.25 | — | 32,768 | 32,768 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1Merge Gateway$173.20
2OpenRouter$280.00
3Eden AI$280.00
4Kilo Gateway$280.00
5NanoGPT$370.00
6Jalapeno Cloud$393.50
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
Toggle (on / off)effort = higheffort = loweffort = mediumbudget_tokens ≥ 1,024 ≤ 81,920
5 / 9 providers expose no reasoning control (reasoning_options: []).
Related models
Qwen3.5 0.8Bsame series$0.06 / $0.12Qwen3.5 4Bsame series$0.10 / $0.20Qwen3.8 27B TEEsame series$0.40 / $3.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiniMax-M2.7cheaper alternative$0.30 / $1.20DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended