What is Mistral Large 4 (Le Chonk)?

Mistral Large 4 (Le Chonk) is a model from Mistral, released on Oct 6, 2026. Mistral Large 4 (Le Chonk), a general-purpose multimodal model available in public preview.

How much does Mistral Large 4 (Le Chonk) cost?

On the Respan gateway, Mistral Large 4 (Le Chonk) costs $0.70 per 1M input tokens and $2.10 per 1M output tokens on Mistral, after gateway discounts.

Which providers serve Mistral Large 4 (Le Chonk) on Respan?

Mistral Large 4 (Le Chonk) is served by Mistral.

What is Mistral Large 4 (Le Chonk)'s context window?

Mistral Large 4 (Le Chonk) accepts up to 1M tokens of context.

How do I use Mistral Large 4 (Le Chonk) with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "mistral/mistral-large-4". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Where does Mistral Large 4 (Le Chonk) rank on the Respan Index?

Mistral Large 4 (Le Chonk) scores 45.0 out of 100 on the Respan Index v1.1, ranking #47 of 161 models. By category: Coding 41.5, Agents 56.0, Reasoning 42.7, Knowledge & language 18.2, and Human preference 54.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

How does Mistral Large 4 (Le Chonk) score on benchmarks?

Mistral Large 4 (Le Chonk) has 21 published benchmark scores, including LiveBench Coding 77.2%, LiveBench Agentic Coding 57.2%, and GPQA Diamond 88.1%. Each score links to where it was published; the data is collected by Respan.

Mistral Large 4 (Le Chonk)

Mistral Large 4 (Le Chonk), a general-purpose multimodal model available in public preview.

Input / output price: $0.70 / $2.10 per 1M
Weekly tokens / requests: 141 / 8
Context: 1M tokens
Released: Oct 6, 2026

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mistral/mistral-large-4".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="mistral/mistral-large-4",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "mistral/mistral-large-4",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "mistral/mistral-large-4",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Mistral`mistral/mistral-large-4`	1M	$0.70/M	$2.10/M	$0.07/M

Is a provider down? Mistral AI status

Pricing

USD per 1M tokens on Mistral, after gateway discounts.

Input: $0.70 per 1M
Output: $2.10 per 1M
Cache read: $0.07 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.70/MMistral

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

17tokens/sacross providers

Faster than 25% of the other 472 models on the gateway

Response latency

Lower is better

0.9sacross providers

Faster than 82% of the other 498 models on the gateway

Benchmarks

The Respan Index plus 21 published scores from 5 sources, each linked to where it was published.

45.0/ 100

Respan Index#47 of 161

161 ranked models. The shaded band is this model's 95% interval, 39.5 to 51.1. Claude Opus 4.6 and Gemini 3.5 Flash fall inside it, so the gap is within the margin of error.

Published scores

Benchmark	Score	Source	Published
LiveBench CodingLiveBench	77.2%	LiveBench	Oct 13, 2026
Terminal-Bench 4.0Vals AI	27.8%	Vals AI	Oct 28, 2026

Benchmark	Score	Source	Published
LiveBench Agentic CodingLiveBench	57.2%	LiveBench	Oct 13, 2026
APEX-AgentsMercor	51.6%	Mercor	Oct 31, 2026

Benchmark	Score	Source	Published
GPQA DiamondEpoch AI	88.1%	Epoch AI	Oct 28, 2026
LiveBench ReasoningLiveBench	83.9%	LiveBench	Oct 13, 2026
LiveBench Data AnalysisLiveBench	76.5%	LiveBench	Oct 13, 2026
Chess PuzzlesEpoch AI	33%	Epoch AI	Oct 28, 2026
Mystery Game PuzzlesEpoch AI	17%	Epoch AI	Oct 28, 2026

Benchmark	Score	Source	Published
OTIS Mock AIME 2024-2025Epoch AI	98.3%	Epoch AI	Oct 28, 2026
LiveBench MathematicsLiveBench	93.6%	LiveBench	Oct 13, 2026
FrontierMath Tiers 1-3 v2Epoch AI	58.6%	Epoch AI	Oct 28, 2026
FrontierMath Tier 4 v2Epoch AI	26.8%	Epoch AI	Oct 28, 2026

Benchmark	Score	Source	Published
LiveBench Instruction FollowingLiveBench	64.8%	LiveBench	Oct 13, 2026
LiveBench LanguageLiveBench	49.6%	LiveBench	Oct 13, 2026
SimpleQA VerifiedEpoch AI	20%	Epoch AI	Oct 13, 2026

Benchmark	Score	Source	Published
Furniture AssemblyEpoch AI	20.8%	Epoch AI	Oct 28, 2026

Benchmark	Score	Source	Published
LMArena WebDevLMArena	1544 Elo · #41 of 113	LMArena	Oct 28, 2026
LMArena EloLMArena	1432 Elo · #80 of 163	LMArena	Oct 28, 2026
LMArena VisionLMArena	1252 Elo · #41 of 87	LMArena	Oct 19, 2026
LMArena AgentLMArena	-0.0602 · #46 of 59	LMArena	Oct 28, 2026