impulse

Mistral Large

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.

API id mistral-large-latestReleased 26 Feb 2024 (Feb 2024)
Input / 1M
$0.50
at Mistral AI
Output / 1M
$1.50
at Mistral AI
Context window
262K
tokens
Max output
262K
tokens per reply
Hosts
7
9 listings
Released
Feb 2024
26 Feb 2024

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.50$1.50
Cached input
90% off input
$0.05

What it costs a month

At Mistral AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$222
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$186
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$312
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,560
Use your own numbers

Where to run it

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

HostIn / out per 1M
Mistral AILab API
mistral-large-latest
$0.50 / $1.50
mistral-large-latest
$2.00 / $6.00
+300% vs headline
mistral-large@2407
$2.00 / $6.00
+300% vs headline
mistral-large
$2.00 / $6.00
+300% vs headline
mistral-large
$3.00 / $10.00
+533% vs headline
mistral-large-latest
$8.00 / $24.00
+1500% vs headline
mistral-large
-
Show 2 more listings: regions, snapshots and variants
Vertex AI
Alias
mistral-large@latest
$2.00 / $6.00
+300% vs headline
Alias
mistral-large@2411-001
$2.00 / $6.00
+300% vs headline

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

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

  • Magistral Small
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    65% less
  • Mistral Vibe Cli Fast
    Mistral AI · on Mistral AI
    $0.15 / $0.60
    Has every key capability
    65% less
  • Zai Glm 5.3 Flash
    Mistral AI · on Mistral AI
    $0.15 / $0.50
    Has every key capability
    68% less

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    38% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    73% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    73% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    65% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    9% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    15% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    30% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    36% less

Call it

Using Mistral AI's API.

Python
from litellm import completion

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

Quick answers

How much does Mistral Large cost?

On Mistral AI, Mistral Large costs $0.50 per million input tokens and $1.50 per million output tokens. Cached input costs $0.05 per million tokens.

Which APIs offer Mistral Large?

Mistral Large runs on 7 APIs: Mistral AI, Azure AI Foundry, Vertex AI, Vercel AI Gateway, IBM watsonx.ai, Azure OpenAI and Snowflake.

What is Mistral Large's context window?

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

Is Mistral Large being retired?

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

What are cheaper alternatives to Mistral Large?

Models that cost less and keep most of what it can do: Magistral Small on Mistral AI (65% less), GPT-5.4 Nano on OpenAI (38% less), Claude Haiku 5.5 on Anthropic (73% less) and Kimi K2.7 Code on CLF AI Gateway (9% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Mistral Large released?

Mistral AI released it on 26 Feb 2024.

What is Mistral Large's API model id?

Use mistral-large-latest with Mistral AI. Other hosts use their own ids: mistral-large@2407 on Vertex AI, mistral-large on Vercel AI Gateway, mistral-large on IBM watsonx.ai, mistral-large on Snowflake.

Sources

Raw catalog entry for mistral-large-latest on Mistral AI
{
  "cache_read_input_token_cost": 5e-8,
  "input_cost_per_token": 5e-7,
  "litellm_provider": "mistral",
  "max_input_tokens": 262144,
  "max_output_tokens": 262144,
  "mode": "chat",
  "output_cost_per_token": 0.0000015,
  "source": "https://docs.mistral.ai/models/mistral-large-3-25-12",
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true
}