Mistral Large 3 2512

What is Mistral Large 3 2512?

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.

Per 1M input / output tokens

$0.50 / $1.50

Starting price

Context window

262K

Up to 210K output per reply

Input

text + image + file

Output: text

What Mistral Large 3 2512 can do

• Tool-using agents

• Structured outputs (JSON)

• Image understanding

• Documents and PDFs

Mistral Large 3 2512 vs similar models: price

What you pay for Mistral Large 3 2512 and the models most like it: the same kind of work, from the families we feature, priced within about three times of it.

• Mistral Large 3 2512 vs DeepSeek V4.1 Flash (1017)

  DeepSeek V4.1 Flash (1017) costs $0.525: 48% less than Mistral Large 3 2512.

  −40% at the top tier

  DeepSeek V4.1 Flash (1017) API 

• Mistral Large 3 2512 vs Gemini 3.8 Flash

  Gemini 3.8 Flash costs $2.025: 2.0× the price of Mistral Large 3 2512.

  −10% at the top tier

  Gemini 3.8 Flash API 

• Mistral Large 3 2512 vs GLM 5.3

  GLM 5.3 costs $2.465: 2.5× the price of Mistral Large 3 2512.

  −25% at the top tier

  GLM 5.3 API 

• Mistral Large 3 2512 vs MiniMax M3

  MiniMax M3 costs $0.75: 25% less than Mistral Large 3 2512.

  MiniMax M3 API 

• Mistral Large 3 2512 vs Qwen3.8 27B

  Qwen3.8 27B costs $1.488: 1.5× the price of Mistral Large 3 2512.

  Qwen3.8 27B API 

Mistral Large 3 2512 specs

The technical card for Mistral Large 3 2512, from the OceanToken catalog.

Context window

262K tokens

262,144

Max output

210K tokens

209,715

Input

text, image, file

Output

text

Reasoning

Not listed yet

Tool calling

Yes

tool_choice

Structured outputs

Yes

response_format

Prompt caching

Reads $0.05

official price, at every tier

Mistral Large 3 2512 model ID and endpoint

OceanToken model ID

mistralai/mistral-large-2512Copied

OpenAI-compatible base URL

https://api.oceantoken.ai/v1Copied

Endpoint

POST /v1/chat/completionsCopied

Mistral Large 3 2512 API pricing

Prices come from the OceanToken catalog as of November 5, 2026. You pay per use from a prepaid balance, with no subscription.

Mistral Large 3 2512 cost calculator

Pick a typical request or enter your own token counts. The calculator uses the starting prices on this page and shows the same workload on the models compared above.

At the starting price (tier 1). Cached input is billed at the cache-read price; cache writes are left out because they depend on how often your prompt prefix changes. Your console shows the rate for your tier.

What a request costs

Input and output tokens at the starting price above, with no caching.

How to use Mistral Large 3 2512 on OceanToken

Three steps from no account to a working request. The same key and balance work for every model in the catalog.

1. 1

   Create an account and get an API key

   Create an OceanToken account, then create a key. One key works for every model your account can use.

   Get API Key 

2. 2

   Add credits

   OceanToken is prepaid: add credits, and each request is billed from that balance. Your console shows the rate for your tier.

   Add credits 

3. 3

   Call Mistral Large 3 2512 from your code

   Point an OpenAI SDK at https://api.oceantoken.ai/v1 and use the model ID mistralai/mistral-large-2512. The code below sends one request.

   from openai import OpenAI
   # Your API Key from the OceanToken console
   client = OpenAI(base_url="https://api.oceantoken.ai/v1",
                   api_key="YOUR_API_KEY")
   reply = client.chat.completions.create(
       model="mistralai/mistral-large-2512",
       messages=[{"role": "user", "content": "Hello"}])
   print(reply.choices[0].message.content)

   Specs, request sample and alternatives in the docs