# Mistral-7B-Instruct-v0.3

> Mistral-7B-Instruct-v0.3 is an open-weight language model from Mistral AI, released on 22 May 2024. It accepts text and generates text, with a 66K-token context window and up to 66K output tokens per response. Mistral AI has deprecated this model.

Source page: https://www.aimodel.directory/models/mistral-7b-instruct-v0-3
Last verified: 18 Nov 2026

## Specifications

- **Developer:** Mistral AI
- **Release date:** 22 May 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Status:** Deprecated (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Context window:** 66K (65,536 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Max output:** 66K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/mistralai/mistral-7b-instruct-v0.3.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of Mistral-7B-Instruct-v0.3?

Mistral-7B-Instruct-v0.3 has a context window of 65,536 tokens (66K) and can generate up to 65,536 tokens in a single response, according to models.dev.

### Is Mistral-7B-Instruct-v0.3 open source?

Mistral-7B-Instruct-v0.3 is an open-weight model. Check the license terms before commercial use.

### When was Mistral-7B-Instruct-v0.3 released?

Mistral AI released Mistral-7B-Instruct-v0.3 on 22 May 2024, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Mistral-7B-Instruct-v0.3", https://www.aimodel.directory/models/mistral-7b-instruct-v0-3