impulse

Ministral 8B 2512

Open weights

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

API id ministral-8b-2512Released 2 Dec 2025 (Dec 2025)
Input / 1M
$0.15
at Mistral AI
Output / 1M
$0.15
at Mistral AI
Context window
262K
tokens
Max output
262K
tokens per reply
Hosts
1
1 listings
Released
Dec 2025
2 Dec 2025

Pricing

List prices at Mistral AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.15
Cached input
90% off input
$0.015

What it costs a month

At Mistral AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$44.10
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$45.00
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$75.60
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$396
Use your own numbers

Where to run it

1 host serve Ministral 8B 2512. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Mistral AILab API
ministral-8b-2512
$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
Assistant prefill
Open weights
License: Apache-2.0
Runs in about 21.4 GB of GPU memory
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 Mistral AI.

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 Mistral AI's API.

Python
from litellm import completion

response = completion(
    model="mistral/ministral-8b-2512",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Ministral 8B 2512 cost?

On Mistral AI, Ministral 8B 2512 costs $0.15 per million input tokens and $0.15 per million output tokens. Cached input costs $0.015 per million tokens.

Which APIs offer Ministral 8B 2512?

Ministral 8B 2512 runs on 1 API: Mistral AI.

What is Ministral 8B 2512's context window?

262K tokens, with up to 262K tokens in one reply.

Is Ministral 8B 2512 being retired?

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

What are cheaper alternatives to Ministral 8B 2512?

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.

When was Ministral 8B 2512 released?

Mistral AI released it on 2 Dec 2025.

What is Ministral 8B 2512's API model id?

Use ministral-8b-2512 with Mistral AI.

Sources

Raw catalog entry for ministral-8b-2512 on Mistral AI
{
  "cache_read_input_token_cost": 1.5e-8,
  "input_cost_per_token": 1.5e-7,
  "litellm_provider": "mistral",
  "max_input_tokens": 262144,
  "max_output_tokens": 262144,
  "mode": "chat",
  "output_cost_per_token": 1.5e-7,
  "source": "https://mistral.ai/pricing",
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true
}