Mistral Large 4
mistral-large-4Pricing
List prices at Mistral AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.70 | $2.10 | |
| Cached input 90% off input | $0.07 | 90% off input |
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
Where to run it
2 hosts serve Mistral Large 4. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Mistral AILab API mistral-large-4 | $0.70 / $2.10 | mistral-large-4 | |
Azure AI FoundryCloud mistral-large-4-latest | $0.70 / $2.10 Retires 27 Oct 2027 | mistral-large-4-latest | 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
- 77% less
- 75% less
- 75% less
Other frontier labs
- 19% less
- 56% less
- 81% less
- 81% less
Open-weight picks
- 35% less
- 39% less
- 50% less
- 54% less
Model line
Newer and older versions, at each lab's own price.
- UndatedMistral Large 2411Latest$2.00 / $6.00
- Nov 2024Mistral Large 2407$2.00 / $6.00
- UndatedMistral Large 2402$4.00 / $12.00
- UndatedMistral Large 4This page$0.70 / $2.10
- Oct 2026Mistral Large 4.0$0.70 / $2.10
- UndatedMistral Large 3$0.50 / $1.50
Call it
Using Mistral AI's API.
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
}