LiteLLMModels

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.

By Mistral AIModel ID watsonx/mistralai/mistral-small-3-1-24b-instruct-2503Prices updated Checked
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.

ProviderModel name in LiteLLMInputOutputContext
IBM watsonx.aisnapshot 2503watsonx/mistralai/mistral-small-3-1-24b-instruct-2503$0.106$0.318128K
Cloudflare Workers AIcloudflare/@cf/mistralai/mistral-small-3.1-24b-instruct$0.351$0.555128K

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

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.

Python SDK
from litellm import completion

response = completion(
    model="watsonx/mistralai/mistral-small-3-1-24b-instruct-2503",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
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 page
Call the proxy
curl 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.