Open 7B Mistral instruction model with function calling
https://router.huggingface.co/v1 mistral-7b-instruct-v0-3 Mistral-7B-Instruct-v0.3 is listed for chat workloads and supports a 32K context window.
Check Hugging Face's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We only found this Mistral-7B-Instruct-v0.3 listing on Hugging Face in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Mistral-7B-Instruct-v0.3 | Check provider | 32K | Native | Credit-metered |
| Model | Provider | Context | Access |
|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct | Hugging Face | 128K | Check provider |
| gemma-3-4b-it | Hugging Face | 131K | Check provider |
| phi-4 | Hugging Face | 16K | Check provider |
| Qwen2.5-Coder-7B-Instruct | Hugging Face | 131K | Check provider |
| Qwen2.5-7B-Instruct | Hugging Face | 131K | Check provider |
Mistral-7B-Instruct-v0.3 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Mistral-7B-Instruct-v0.3 appears in the free model catalog for Hugging Face, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is mistral-7b-instruct-v0-3.
The listed free tier limit is Credit-metered. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 32K tokens with up to 4K output tokens.
Mistral 7B Instruct v0.3 is a compact, efficient open model available free on Hugging Face's Serverless Inference API. At 7B parameters, it is lightweight and fast, best suited for straightforward chat, text classification, and simple generation tasks. Context is limited to 32K — adequate for conversations and short documents but not long-form analysis. Uses Hugging Face's native API format (not OpenAI-compatible); rate limits are approximately 1,000 requests per day. Registration required.
For API keys, setup steps, and provider-level limits, see the Hugging Face provider page.