Mistral 7B
Mistral 7B is a language model with 7B parameters from Mistral AI. It is currently free at 5 providers with up to 33K tokens of context. Its weights are open, so it can also run locally.
- Developer
- Mistral AI
- Parameters
- 7B
- Context
- 33K tokens
- Type
- Text
- License
- Open weights
- Free since
- September 19, 2026
Where to use Mistral 7B for free
Each row is a separate free endpoint with its own limits.
| Provider | Context | Limit | Card | |
|---|---|---|---|---|
 Together AI mistralai/Mistral-7B-v0.1 |
33K | Fair use (depends on server load) | — | Open |
 Cloudflare Workers AI @cf/mistral/mistral-7b-instruct-v0.3 |
33K | 10,000 req/day | — | Open |
 Hugging Face mistralai/Mistral-7B-v0.3 |
33K | Fair use (depends on server load) | No | Open |
 NVIDIA Build mistralai/mistral-7b-instruct-v0.3 |
— | Free serverless inference for development; limits and model availability may change. | No | Open |
 UnoRouter mistral-7b-instruct:free |
25K | No-card free models use shared capacity and per-model limits; availability can change. | No | Open |
Quick start
curl https://api.together.xyz/v1/chat/completions \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/Mistral-7B-v0.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.together.xyz/v1",
api_key="YOUR_TOGETHER_API_KEY",
)
reply = client.chat.completions.create(
model="mistralai/Mistral-7B-v0.1",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.together.xyz/v1",
apiKey: process.env.TOGETHER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "mistralai/Mistral-7B-v0.1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · Mistral 7B Instruct
Similar free models
FAQ
Is Mistral 7B free?
Yes. As of September 26, 2026, Mistral 7B is free at Together AI, Cloudflare Workers AI, Hugging Face, NVIDIA Build, UnoRouter. Each provider has its own limits — see the table above.
What is the context window of Mistral 7B?
The largest context among free routes is 32,768 tokens. Some providers cap it lower.
How do I call Mistral 7B via API?
Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID mistralai/Mistral-7B-v0.1, and a Together AI key.
How good is Mistral 7B?
Artificial Analysis Intelligence Index: 5.0, GPQA Diamond: 18%. For comparison, the strongest free model in the catalog right now is GLM 5.3.
Is Mistral 7B open-weight?
Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.