Qwen3 235B A22B Instruct 2507
Summary
Qwen3 235B A22B Instruct 2507 is an open-weight language model from Alibaba (Qwen), released on 21 Jul 2025. It accepts text and generates text, with a 262K-token context window and up to 8K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.09 per million input tokens and $0.55 per million output tokens (DeepInfra), across 5 providers we track.
Qwen instruction model for multilingual chat, reasoning, and tool use
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Alibaba (Qwen) |
|---|---|
| Release date | 21 Jul 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 235B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 8K tokens [models.dev] |
| Knowledge cutoff | Jul 2025 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | Qwen/Qwen3-235B-A22B-Instruct-2507 [Hugging Face] |
Qwen3 235B A22B Instruct 2507 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepInfra Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.09 | $0.55 | – | 262K | models.dev, 18 Nov 2026 |
| OpenRouter qwen/qwen3-235b-a22b-2507 | $0.14 | $0.80 | $0.05 | 131K | OpenRouter, 18 Nov 2026 |
| Nebius AI Studio Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.20 | $0.60 | $0.20 | 262K | models.dev, 18 Nov 2026 |
| Amazon Bedrock qwen.qwen3-235b-a22b-2507-v1:0 | $0.22 | $0.88 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.85 | $2.56 | – | 262K | models.dev, 18 Nov 2026 |
Running Qwen3 235B A22B Instruct 2507 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 | 252 GB | 257 GB |
| FP16 / BF16 (16-bit) | 470 GB | 473 GB | 477 GB |
At 4-bit with an 8K conversation, Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507?
Qwen3 235B A22B Instruct 2507 has a context window of 262,144 tokens (262K) and can generate up to 8,192 tokens in a single response, according to models.dev.
How much does the Qwen3 235B A22B Instruct 2507 API cost?
Qwen3 235B A22B Instruct 2507 is listed from $0.09 per million input tokens and $0.55 per million output tokens (DeepInfra). Prices last verified 18 Nov 2026.
Is Qwen3 235B A22B Instruct 2507 open source?
Qwen3 235B A22B Instruct 2507 is an open-weight model: its weights are published on Hugging Face as Qwen/Qwen3-235B-A22B-Instruct-2507 under the apache-2.0 license. Check the license terms before commercial use.
When was Qwen3 235B A22B Instruct 2507 released?
Alibaba (Qwen) released Qwen3 235B A22B Instruct 2507 on 21 Jul 2025, according to models.dev.
Which providers offer Qwen3 235B A22B Instruct 2507?
We track Qwen3 235B A22B Instruct 2507 on 5 providers: DeepInfra, OpenRouter, Nebius AI Studio, Amazon Bedrock, Hugging Face Inference Providers.
How much VRAM does Qwen3 235B A22B Instruct 2507 need?
About 145 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 252 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 |
|---|---|---|---|---|---|---|
| Mistral Small 3.2 24B | Mistral AI | 20 Jun 2025 | 256K | $0.10 | $0.30 | Open |
| DeepSeek V3.2 Exp | DeepSeek | 29 Sept 2025 | 164K | $0.27 | $0.41 | Open |
| Jamba Mini | AI21 Labs | 8 Jan 2026 | 256K | $0.20 | $0.40 | Open |
| GLM-4.5-Air | Zhipu AI (Z.ai) | 28 Jul 2025 | 131K | $0.13 | $0.85 | Open |
| Ministral 14B | Mistral AI | 2 Dec 2025 | 262K | $0.20 | $0.20 | Open |
| DeepSeek V3.1 | DeepSeek | 21 Aug 2025 | 164K | $0.25 | $0.95 | Open |
Change history
- No longer listed on vercel
- OpenRouter price changed: input $0.09 → $0.14, output $0.55 → $0.80 per 1M tokens
- Release date changed from 25 Jul 2025 to 21 Jul 2025
- Nebius AI Studio price changed: input $0.20 → $0.20, output $0.60 → $0.60 per 1M tokens
- Now listed on vercel
- No longer listed on novita-ai
- Context window changed from 131K to 262K
- Max output changed from 16K to 8K
- Release date changed from 22 Jul 2025 to 25 Jul 2025
- Knowledge cutoff changed from Apr 2025 to Jul 2025
- OpenRouter price changed: input $0.09 → $0.09, output $0.35 → $0.55 per 1M tokens
Sources
- https://openrouter.ai/qwen/qwen3-235b-a22b-2507
- https://github.com/sst/models.dev/blob/dev/providers/nebius/models/Qwen/Qwen3-235B-A22B-Instruct-2507.toml
- https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/Qwen/Qwen3-235B-A22B-Instruct-2507.toml
- https://github.com/sst/models.dev/blob/dev/providers/amazon-bedrock/models/qwen.qwen3-235b-a22b-2507-v1:0.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/Qwen/Qwen3-235B-A22B-Instruct-2507.toml