LiteLLMModels

Voxtral Mini 3B API Pricing

As of October 10, 2026, Voxtral Mini 3B costs $0.04 per 1M input tokens and $0.04 per 1M output tokens on Amazon Bedrock. It has a 32,768-token context window and returns up to 8,192 tokens per response.

By Mistral AIModel ID mistral.voxtral-mini-3b-2507Prices updated Checked
Scheduled for deprecation: Amazon Bedrock lists March 30, 2027 as the deprecation date for mistral.voxtral-mini-3b-2507.
Input
$0.04 / 1M tokens
Output
$0.04 / 1M tokens
Context window
32,768 tokens
Max output
8,192 tokens
Providers
1
Added to LiteLLM
December 2025

Voxtral Mini 3B 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.

ProviderModel name in LiteLLMInputOutputContext
Amazon Bedrocksnapshot 2507mistral.voxtral-mini-3b-2507$0.04$0.0432K

Other Voxtral Mini 3B prices on Amazon Bedrock

Flex input$0.02 per 1M tokens
Flex output$0.02 per 1M tokens

What Voxtral Mini 3B costs in practice

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

Amazon Bedrock$0.10

Voxtral Mini 3B features

Use Voxtral Mini 3B with LiteLLM

Call Voxtral Mini 3B 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="mistral.voxtral-mini-3b-2507",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: voxtral-mini-3b
    litellm_params:
      model: mistral.voxtral-mini-3b-2507
      aws_region_name: os.environ/AWS_REGION_NAME
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": "voxtral-mini-3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Voxtral Mini 3B FAQ

How much does Voxtral Mini 3B cost?

Voxtral Mini 3B costs $0.04 per 1M input tokens and $0.04 per 1M output tokens on Amazon Bedrock.

What is the context window of Voxtral Mini 3B?

Voxtral Mini 3B has a 32,768-token context window and returns up to 8,192 tokens per response.

Which providers offer Voxtral Mini 3B?

Voxtral Mini 3B is available from Amazon Bedrock through LiteLLM, using the model name mistral.voxtral-mini-3b-2507.

How do I call Voxtral Mini 3B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral.voxtral-mini-3b-2507", 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 Voxtral Mini 3B support?

Voxtral Mini 3B supports audio input.

When did LiteLLM add Voxtral Mini 3B?

Voxtral Mini 3B was added to LiteLLM's model price file in December 2025.

Is Voxtral Mini 3B being deprecated?

Amazon Bedrock lists a deprecation date of March 30, 2027 for mistral.voxtral-mini-3b-2507.

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: Amazon Bedrock.

Provider pages: Amazon Bedrock.