impulse

Mistral Large 4

API id mistral-large-4
Input / 1M
$0.70
at Mistral AI
Output / 1M
$2.10
at Mistral AI
Context window
1M
tokens
Max output
1M
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.70$2.10
Cached input
90% off input
$0.07

What it costs a month

At Mistral AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$311
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$260
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$437
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,184
Use your own numbers

Where to run it

2 hosts serve Mistral Large 4. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Mistral AILab API
mistral-large-4
$0.70 / $2.10
mistral-large-4-latest
$0.70 / $2.10
Retires 27 Oct 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
TextImages
Produces
Text
Effort settings the source lists
lowmediumhigh
Features
Assistant prefillPrompt caching

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

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    19% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    56% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    81% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    81% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    35% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    39% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    50% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    54% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedMistral Large 2411Latest$2.00 / $6.00
  2. Nov 2024Mistral Large 2407$2.00 / $6.00
  3. UndatedMistral Large 2402$4.00 / $12.00
  4. UndatedMistral Large 4This page$0.70 / $2.10
  5. Oct 2026Mistral Large 4.0$0.70 / $2.10
  6. UndatedMistral Large 3$0.50 / $1.50

Call it

Using Mistral AI's API.

Python
from litellm import completion

response = completion(
    model="mistral/mistral-large-4",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mistral Large 4 cost?

On Mistral AI, Mistral Large 4 costs $0.70 per million input tokens and $2.10 per million output tokens. Cached input costs $0.07 per million tokens.

Which APIs offer Mistral Large 4?

Mistral Large 4 runs on 2 APIs: Mistral AI and Azure AI Foundry.

What is Mistral Large 4's context window?

1M tokens, with up to 1M tokens in one reply.

Is Mistral Large 4 being retired?

Azure AI Foundry retires it on 27 Oct 2027. 1 host keeps serving it.

Is there a newer version of Mistral Large 4?

Yes. Mistral Large 2411 is the newest model in this line.

What are cheaper alternatives to Mistral Large 4?

Models that cost less and keep most of what it can do: Zai Glm 5.3 Flash on Mistral AI (77% less), Gemini 3.5 Flash Lite on Google AI Studio (19% less), GPT-5.4 Nano on OpenAI (56% less) and Kimi K2.7 Code on CLF AI Gateway (35% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Mistral Large 4's API model id?

Use mistral-large-4 with Mistral AI. Other hosts use their own ids: mistral-large-4-latest on Azure AI Foundry.

Sources

Raw catalog entry for mistral-large-4 on Mistral AI
{
  "cache_read_input_token_cost": 7e-8,
  "input_cost_per_token": 7e-7,
  "litellm_provider": "mistral",
  "max_input_tokens": 1048576,
  "max_output_tokens": 1048576,
  "mode": "chat",
  "output_cost_per_token": 0.0000021,
  "reasoning_effort_levels": [
    "low",
    "medium",
    "high"
  ],
  "source": "https://docs.mistral.ai/models/mistral-large-4-0",
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true
}