impulse

Ministral 3 8B Instruct

Open weights
API id mistral.ministral-3-8b-instruct
Input / 1M
$0.15
at Amazon Bedrock
Output / 1M
$0.15
at Amazon Bedrock
Context window
128K
tokens
Max output
8K
tokens per reply
Hosts
1
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.15$0.15
Batch
53% off
$0.07$0.07
Flex
53% off
$0.07$0.07
Priority
73% more
$0.26$0.26

What it costs a month

At Amazon Bedrock list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$56.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$77.40
  • Coding agent1,000 requests a day, 40K in / 2K out$189
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$185
Use your own numbers

Where to run it

1 host serve Ministral 3 8B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
mistral.ministral-3-8b-instruct
$0.15 / $0.15
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
mistral.ministral-3-8b-instruct
$0.15 / $0.15

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
TextImages
Produces
Text
Features
Native structured output
Open weights
License: Apache-2.0
Runtimes: Ollama, llama.cpp, vLLM

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.ministral-3-8b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Ministral 3 8B Instruct cost?

On Amazon Bedrock, Ministral 3 8B Instruct costs $0.15 per million input tokens and $0.15 per million output tokens.

Which APIs offer Ministral 3 8B Instruct?

Ministral 3 8B Instruct runs on 1 API: Amazon Bedrock.

What is Ministral 3 8B Instruct's context window?

128K tokens, with up to 8K tokens in one reply.

Is Ministral 3 8B Instruct being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Ministral 3 8B Instruct?

Models that cost less and keep most of what it can do: DeepSeek V4.1 Flash on Sail (5% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Ministral 3 8B Instruct's API model id?

Use mistral.ministral-3-8b-instruct with Amazon Bedrock.

Sources

Raw catalog entry for mistral.ministral-3-8b-instruct on Amazon Bedrock
{
  "input_cost_per_token": 1.5e-7,
  "input_cost_per_token_batches": 7e-8,
  "input_cost_per_token_flex": 7e-8,
  "input_cost_per_token_priority": 2.6e-7,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 128000,
  "max_output_tokens": 8000,
  "mode": "chat",
  "output_cost_per_token": 1.5e-7,
  "output_cost_per_token_batches": 7e-8,
  "output_cost_per_token_flex": 7e-8,
  "output_cost_per_token_priority": 2.6e-7,
  "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
  "supports_audio_input": false,
  "supports_function_calling": true,
  "supports_system_messages": true,
  "supports_native_structured_output": true,
  "supports_response_schema": true,
  "supports_vision": true
}