Devstral Medium API Pricing

Devstral Medium pricing by provider

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

What Devstral Medium costs in practice

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

100 long-document requests with 100,000 input and 2,000 output tokens each

Devstral Medium features

• Function calling
• Structured output

Use Devstral Medium with LiteLLM

Call Devstral Medium 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="mistral/devstral-medium-latest",
    messages=[{"role": "user", "content": "Hello!"}],
)

model_list:
  - model_name: devstral-medium
    litellm_params:
      model: mistral/devstral-medium-latest
      api_key: os.environ/MISTRAL_API_KEY

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

Devstral Medium FAQ

More Mistral AI models

• Mistral Large 4$0.68 / $2.09 per 1M tokens
• Mistral Code$0.30 / $0.90 per 1M tokens
• Mistral Code Agent$0.40 / $2 per 1M tokens
• Mistral Code Fim$0.30 / $0.90 per 1M tokens
• Mistral Vibe Cli$1.50 / $7.50 per 1M tokens
• Mistral Vibe Cli Fast$0.15 / $0.60 per 1M tokens
• Mistral Vibe Cli With Tools$1.50 / $7.50 per 1M tokens
• Voxtral Small$0.10 / $0.40 per 1M tokens