# Qwen3 235B A22B Instruct 2507

> Qwen3 235B A22B Instruct 2507 is an open-weight language model from Alibaba (Qwen), released on 22 Jul 2025. It accepts text and generates text, with a 131K-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.09 per million input tokens and $0.35 per million output tokens (OpenRouter), across 6 providers we track.

Source page: https://www.aimodel.directory/models/qwen3-235b-a22b-instruct-2507
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Alibaba (Qwen)
- **Release date:** 22 Jul 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)
- **Parameters:** 235B (source: Hugging Face, https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)
- **Context window:** 131K (131,072 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Knowledge cutoff:** Apr 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/qwen/qwen3-235b-a22b-instruct-2507.toml)
- **Hugging Face:** Qwen/Qwen3-235B-A22B-Instruct-2507 (source: Hugging Face, https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.09 | $0.35 | $0.02 | 262K |
| DeepInfra | $0.09 | $0.55 | – | 262K |
| Novita AI | $0.09 | $0.58 | – | 131K |
| Nebius AI Studio | $0.20 | $0.60 | – | 262K |
| Amazon Bedrock | $0.22 | $0.88 | – | 262K |
| Hugging Face Inference Providers | $0.85 | $2.56 | – | 262K |

## FAQ

### What is the context window of Qwen3 235B A22B Instruct 2507?

Qwen3 235B A22B Instruct 2507 has a context window of 131,072 tokens (131K) and can generate up to 16,384 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 $0.35 per million output tokens (OpenRouter). Prices last verified 4 Oct 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 22 Jul 2025, according to models.dev.

### Which providers offer Qwen3 235B A22B Instruct 2507?

We track Qwen3 235B A22B Instruct 2507 on 6 providers: OpenRouter, DeepInfra, Novita AI, Nebius AI Studio, Amazon Bedrock, Hugging Face Inference Providers.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Qwen3 235B A22B Instruct 2507", https://www.aimodel.directory/models/qwen3-235b-a22b-instruct-2507