impulse

Voxtral Mini 3B 2507

API id mistral.voxtral-mini-3b-2507
Amazon Bedrock retires it on 30 Mar 2027 (in 132 days). No API serves it after that.
Input / 1M
$0.04
at Amazon Bedrock
Output / 1M
$0.04
at Amazon Bedrock
Context window
33K
tokens
Max output
8K
tokens per reply
Hosts
1
5 listings
Released
-
date not published

Pricing

List prices at Amazon Bedrock, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.04$0.04
Batch
50% off
$0.02$0.02
Flex
50% off
$0.02$0.02
Priority
75% more
$0.07$0.07

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$15.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$20.64
  • Coding agent1,000 requests a day, 40K in / 2K out$50.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$52.80
Use your own numbers

Where to run it

1 host serve Voxtral Mini 3B 2507. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
mistral.voxtral-mini-3b-2507
$0.04 / $0.04
Retires 30 Mar 2027
Show 4 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
mistral.voxtral-mini-3b-2507
$0.04 / $0.04
Retires 30 Mar 2027
ap-southeast-2
mistral.voxtral-mini-3b-2507
$0.0412 / $0.0412
+3% vs headline
Retires 30 Mar 2027
ap-northeast-1
mistral.voxtral-mini-3b-2507
$0.05 / $0.05
+25% vs headline
Retires 30 Mar 2027
eu-west-2
mistral.voxtral-mini-3b-2507
$0.06 / $0.06
+50% vs headline
Retires 30 Mar 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextAudio
Produces
Text
Features
Audio inputNative structured output

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Amazon Bedrock.

Smaller Mistral AI models

No cheaper Mistral AI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

Call it

Using Amazon Bedrock's API.

Python
from litellm import completion

response = completion(
    model="bedrock/mistral.voxtral-mini-3b-2507",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Voxtral Mini 3B 2507 cost?

On Amazon Bedrock, Voxtral Mini 3B 2507 costs $0.04 per million input tokens and $0.04 per million output tokens.

Which APIs offer Voxtral Mini 3B 2507?

Voxtral Mini 3B 2507 runs on 1 API: Amazon Bedrock.

What is Voxtral Mini 3B 2507's context window?

33K tokens, with up to 8K tokens in one reply.

Is Voxtral Mini 3B 2507 being retired?

Amazon Bedrock retires it on 30 Mar 2027. No API serves it after that.

What are cheaper alternatives to Voxtral Mini 3B 2507?

Models that cost less and keep most of what it can do: Llama 3.1 8B on LlamaGate (12% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Voxtral Mini 3B 2507's API model id?

Use mistral.voxtral-mini-3b-2507 with Amazon Bedrock.

Sources

Raw catalog entry for mistral.voxtral-mini-3b-2507 on Amazon Bedrock
{
  "deprecation_date": "2027-03-30",
  "deprecation_source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-lifecycle-legacy.html",
  "input_cost_per_token": 4e-8,
  "input_cost_per_token_batches": 2e-8,
  "input_cost_per_token_flex": 2e-8,
  "input_cost_per_token_priority": 7e-8,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 32768,
  "max_output_tokens": 8192,
  "mode": "chat",
  "output_cost_per_token": 4e-8,
  "output_cost_per_token_batches": 2e-8,
  "output_cost_per_token_flex": 2e-8,
  "output_cost_per_token_priority": 7e-8,
  "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
  "supports_audio_input": true,
  "supports_system_messages": true,
  "supports_native_structured_output": true
}