Mistral 7B API Pricing

Mistral 7B pricing by provider

2 listings across 2 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

What Mistral 7B costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Use Mistral 7B with LiteLLM

Call Mistral 7B through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

from litellm import completion

response = completion(
    model="fireworks_ai/accounts/fireworks/models/mistral-7b",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: mistral-7b
    litellm_params:
      model: fireworks_ai/accounts/fireworks/models/mistral-7b
      api_key: os.environ/FIREWORKS_AI_API_KEY

curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "mistral-7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Mistral 7B FAQ

More Mistral AI models

• Mistral 7B Instruct V0.2 LoraFree
• Mistral 7B V0.3$0.10 / $0.15 per 1M tokens
• Mistral 7B Instruct 4K$0.20 / $0.20 per 1M tokens
• Mistral 7B Instruct V3$0.20 / $0.20 per 1M tokens
• Mistral 7B V0p2$0.20 / $0.20 per 1M tokens
• Mistral 7B Instruct V0.3$0.10 / $0.10 per 1M tokens
• Mistral 7B Instruct V0.2Free
• Mistral 7B V0.1$0.05 / $0.25 per 1M tokens