Mistral Small 3.1 24B Instruct API Pricing
As of October 10, 2026, Mistral Small 3.1 24B Instruct costs $0.106 per 1M input tokens and $0.318 per 1M output tokens from IBM watsonx.ai, the lowest of 2 providers. It has a 131,072-token context window and returns up to 16,384 tokens per response.
- Input
- $0.106 / 1M tokens
- Output
- $0.318 / 1M tokens
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- Providers
- 2
- Added to LiteLLM
- April 2025
Mistral Small 3.1 24B Instruct 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.
| Provider | Model name in LiteLLM | Input | Output | Context |
|---|---|---|---|---|
| IBM watsonx.aisnapshot 2503 | watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 | $0.106 | $0.318 | 128K |
| Cloudflare Workers AI | cloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct | $0.351 | $0.555 | 128K |
What Mistral Small 3.1 24B Instruct costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| IBM watsonx.ai | $0.371 |
| Cloudflare Workers AI | $0.9795 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| IBM watsonx.ai | $1.124 |
| Cloudflare Workers AI | $3.621 |
Mistral Small 3.1 24B Instruct features
- Function calling
- Parallel tool calls
- Image input
Use Mistral Small 3.1 24B Instruct with LiteLLM
Call Mistral Small 3.1 24B Instruct 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="watsonx/mistralai/mistral-small-3-1-24b-instruct-2503",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: mistral-small-3-1-24b-instruct
litellm_params:
model: watsonx/mistralai/mistral-small-3-1-24b-instruct-2503
# credentials: see the provider's LiteLLM docs pagecurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "mistral-small-3-1-24b-instruct",
"messages": [{"role": "user", "content": "Hello!"}]
}'Mistral Small 3.1 24B Instruct FAQ
How much does Mistral Small 3.1 24B Instruct cost?
Mistral Small 3.1 24B Instruct costs $0.106 per 1M input tokens and $0.318 per 1M output tokens from IBM watsonx.ai, the lowest of 2 providers.
What is the context window of Mistral Small 3.1 24B Instruct?
Mistral Small 3.1 24B Instruct has a 131,072-token context window and returns up to 16,384 tokens per response.
Which providers offer Mistral Small 3.1 24B Instruct?
Mistral Small 3.1 24B Instruct is available from 2 providers through LiteLLM: IBM watsonx.ai and Cloudflare Workers AI. The lowest price is on IBM watsonx.ai.
How do I call Mistral Small 3.1 24B Instruct with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="watsonx/mistralai/mistral-small-3-1-24b-instruct-2503", 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 Mistral Small 3.1 24B Instruct support?
Mistral Small 3.1 24B Instruct supports function calling and parallel tool calls. It does not support image input.
When did LiteLLM add Mistral Small 3.1 24B Instruct?
Mistral Small 3.1 24B Instruct was added to LiteLLM's model price file in April 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: IBM watsonx.ai, Cloudflare Workers AI.
Provider pages: IBM watsonx.ai, Cloudflare Workers AI.
