Qwen3 VL 235B A22B Instruct
Summary
Qwen3 VL 235B A22B Instruct is an open-weight language model from Alibaba (Qwen), released on 23 Sept 2025. It accepts text and images and generates text, with a 262K-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.20 per million input tokens and $0.88 per million output tokens (DeepInfra), across 4 providers we track.
Qwen vision-language instruct model for visual reasoning, documents, and agent tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 23 Sept 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 236B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 262K tokens [models.dev] |
| Knowledge cutoff | 31 Mar 2025 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3-VL-235B-A22B-Instruct [Hugging Face] |
Qwen3 VL 235B A22B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen3-VL-235B-A22B-Instruct | $0.20 | $0.88 | $0.11 | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-vl-235b-a22b-instruct | $0.21 | $1.90 | $0.10 | 131K | OpenRouter, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-VL-235B-A22B-Instruct | $0.30 | $1.50 | – | 131K | models.dev, 18 Nov 2026 |
| Amazon Bedrock qwen.qwen3-vl-235b-a22b | $0.53 | $2.66 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3 VL 235B A22B Instruct locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 143 GB | 145 GB | 150 GB |
| Q8_0 (8-bit) | 250 GB | 253 GB | 258 GB |
| FP16 / BF16 (16-bit) | 471 GB | 474 GB | 478 GB |
At 4-bit with an 8K conversation, Qwen3 VL 235B A22B Instruct needs about 145 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Qwen3 VL 235B A22B Instruct?
Qwen3 VL 235B A22B Instruct has a context window of 262,144 tokens (262K) and can generate up to 262,000 tokens in a single response, according to models.dev.
How much does the Qwen3 VL 235B A22B Instruct API cost?
Qwen3 VL 235B A22B Instruct is listed from $0.20 per million input tokens and $0.88 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is Qwen3 VL 235B A22B Instruct open source?
Qwen3 VL 235B A22B Instruct is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-VL-235B-A22B-Instruct under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3 VL 235B A22B Instruct released?
Alibaba (Qwen) released Qwen3 VL 235B A22B Instruct on 23 Sept 2025, according to models.dev.
Which providers offer Qwen3 VL 235B A22B Instruct?
We track Qwen3 VL 235B A22B Instruct on 4 providers: DeepInfra, OpenRouter, Hugging Face Inference Providers, Amazon Bedrock.
How much VRAM does Qwen3 VL 235B A22B Instruct need?
About 145 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 253 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| DeepSeek V3.1 Terminus | DeepSeek | 22 Sept 2025 | 164K | $0.27 | $1 | Open |
| DeepSeek V3.1 | DeepSeek | 21 Aug 2025 | 164K | $0.25 | $0.95 | Open |
| Gemma Sea Lion V4 27B It | Aisingapore | 23 Sept 2025 | 128K | $0.35 | $0.56 | Open |
| Cydonia 24B V4.1 | Thedrummer | 27 Sept 2025 | 131K | $0.30 | $0.50 | Open |
| GLM-4.6 | Zhipu AI (Z.ai) | 30 Sept 2025 | 205K | $0.50 | $2 | Open |
| Kimi-K2-Instruct-0905 | Moonshot AI | 5 Sept 2025 | 262K | $0.60 | $2.50 | Open |
Change history
- Max output changed from 33K to 262K
- Context window changed from 131K to 262K
- Context window changed from 262K to 131K
- Max output changed from 262K to 33K
- Context window changed from 131K to 262K
- Max output changed from 33K to 262K
- Context window changed from 262K to 131K
- Max output changed from 262K to 33K
- Max output changed from 33K to 262K
- Context window changed from 131K to 262K
- Context window changed from 262K to 131K
- Context window changed from 131K to 262K
- Context window changed from 262K to 131K
- Max output changed from 262K to 33K
- Max output changed from 33K to 262K
- Max output changed from 262K to 33K
- Max output changed from 33K to 262K
- Context window changed from 131K to 262K
- Max output changed from 262K to 33K
- Context window changed from 262K to 131K
- Max output changed from 33K to 262K
- Max output changed from 262K to 33K
- Context window changed from 131K to 262K
- Max output changed from 33K to 262K
- Context window changed from 262K to 131K
Sources
- https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/qwen.qwen3-vl-235b-a22b.toml
- https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3-VL-235B-A22B-Instruct.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-VL-235B-A22B-Instruct.toml