Devstral Small API Pricing
As of October 10, 2026, Devstral Small costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Mistral AI, with cache reads at $0.01 per 1M tokens. Across 3 providers on LiteLLM, the input price ranges from $0.07 to $0.10. It has a 256,000-token context window and returns up to 256,000 tokens per response.
- Input
- $0.10 / 1M tokens
- Output
- $0.30 / 1M tokens
- Cache read
- $0.01 / 1M tokens
- Context window
- 256,000 tokens
- Max output
- 256,000 tokens
- Providers
- 3
- Added to LiteLLM
- May 2025
Devstral Small pricing by provider
3 listings across 3 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| Mistral AIlatest alias | mistral/devstral-small-latest | $0.10 | $0.30 | $0.01 | 256K |
| Fireworks AI †snapshot 2505 | fireworks_ai/accounts/fireworks/models/devstral-small-2505 | $0.90 | $0.90 | – | 128K |
| Vercel AI Gateway | vercel_ai_gateway/mistral/devstral-small | $0.07 | $0.28 | – | 128K |
† This price differs from the other providers by more than 8x and is left out of the headline price. Check the provider's pricing page.
What Devstral Small costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Mistral AI | $0.35 |
| Vercel AI Gateway | $0.28 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Mistral AI | $1.06 |
| Vercel AI Gateway | $0.756 |
Devstral Small features
- Function calling
- Structured output
Use Devstral Small with LiteLLM
Call Devstral Small 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-small-latest",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: devstral-small
litellm_params:
model: mistral/devstral-small-latest
api_key: os.environ/MISTRAL_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "devstral-small",
"messages": [{"role": "user", "content": "Hello!"}]
}'Devstral Small FAQ
How much does Devstral Small cost?
Devstral Small costs $0.10 per 1M input tokens and $0.30 per 1M output tokens on Mistral AI, with cache reads at $0.01 per 1M tokens. Across 3 providers on LiteLLM, the input price ranges from $0.07 to $0.10.
What is the context window of Devstral Small?
Devstral Small has a 256,000-token context window and returns up to 256,000 tokens per response.
Which providers offer Devstral Small?
Devstral Small is available from 3 providers through LiteLLM: Mistral AI, Fireworks AI and Vercel AI Gateway. The lowest price is on Vercel AI Gateway.
How do I call Devstral Small with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="mistral/devstral-small-latest", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does Devstral Small support?
Devstral Small supports function calling and structured output.
When did LiteLLM add Devstral Small?
Devstral Small was added to LiteLLM's model price file in May 2025.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
LiteLLM docs: Mistral AI, Fireworks AI, Vercel AI Gateway.
Provider pages: Mistral AI, Fireworks AI, Vercel AI Gateway.
