LLM Perks

Mixtral 8x7b

Mistral AI · All Mistral models
Free right now Mid-size
Open weights

Mixtral 8x7b is a language model with 46.7B parameters from Mistral AI. It is currently free at 1 provider with up to 33K tokens of context. Its weights are open, so it can also run locally.

Developer
Mistral AI
Parameters
46.7B / 12.9B active
Context
33K tokens
Type
Text
License
Open weights

Where to use Mixtral 8x7b for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
Together AI
mistralai/Mixtral-8x7B-Instruct-v0.1-FP8-Lora
33K Fair use (depends on server load) — 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/Mixtral-8x7B-Instruct-v0.1-FP8-Lora",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for Together AI. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
5.1
GPQA Diamond
29.2%
Humanity's Last Exam
4.7%

Source: Artificial Analysis · Mixtral 8x7B Instruct

Similar free models

FAQ

Is Mixtral 8x7b free?

Yes. As of September 26, 2026, Mixtral 8x7b is free at Together AI. Each provider has its own limits — see the table above.

What is the context window of Mixtral 8x7b?

The largest context among free routes is 32,768 tokens. Some providers cap it lower.

How do I call Mixtral 8x7b via API?

Use any OpenAI-compatible client with base URL https://api.together.xyz/v1, model ID mistralai/Mixtral-8x7B-Instruct-v0.1-FP8-Lora, and a Together AI key.

How good is Mixtral 8x7b?

Artificial Analysis Intelligence Index: 5.1, GPQA Diamond: 29%. For comparison, the strongest free model in the catalog right now is GLM 5.3.

Is Mixtral 8x7b open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.