Mistral

Mistral Medium 3.5

CTX262K

59Quality

Reasoning · Vision · Tools

Input$1.50/M

Output$7.50/M

Balanced Mistral model for enterprise assistants, multilingual work, and tools

Open weightsApache 2.0898/1044

Drag to turn

MistralTextUncommon

Mistral Medium 3.5

Balanced Mistral model for enterprise assistants, multilingual work, and tools

mistral-medium-2604

Type: Text
Quality: 59 · Top 41% on the Epoch Capabilities Index
Context window: 262,144 tokens
Max output: 262,144 tokens
Input price: $1.50 / 1M tokens
Output price: $7.50 / 1M tokens
Cache read: $0.15 / 1M tokens
Cache write: —
Released: Apr 29, 2026
Knowledge cutoff: —
Takes in: Text, Image
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Open weights
License: Apache 2.0
Rarity: Uncommon
Set number: 898/1044

Open Mistral docs Quality 59 Where to run it 19 Evolution 3/3 Meet its creature Battle Qwen3.7 Max

No matching Hugging Face repo was found, so this shows Mistral’s usual open-weight license. Check the model card before relying on it. Specs from models.dev, last changed Oct 19, 2026. Official source: docs.mistral.ai.

How good is it?

Public leaderboard scores for Mistral Medium 3.5, refreshed daily from Epoch AI and LMArena.

Top 41% of the 277 models on the Epoch Capabilities Index: #113.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#113 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.141.5 index
LMArena Text#112 of 416
People compare two anonymous answers and vote for the better one.1,421 rating
LMArena Text · Coding#83 of 411
The text arena’s coding prompts only.1,461 rating
LMArena Text · Math#99 of 400
The text arena’s math prompts only.1,431 rating
LMArena Text · Creative writing#140 of 414
The text arena’s creative writing prompts only.1,374 rating
LMArena WebDev#129 of 145
Each model builds a web app from the same prompt; people pick the better one.1,264 rating
LMArena Vision#82 of 165
Questions about images, voted by people.1,223 rating

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

19 providers sell Mistral Medium 3.5 through an API. Prices are per million tokens, cheapest first.

Cheapestevroc$1.73 in · $6.90 out
Free to try2 providersKenari, Nvidia
From the labMistral$1.50 in · $7.50 out

API providers

Provider	Input	Output	Context
KenariFree`mistral-medium-3-5:free`	Free	Free	262K
NvidiaFree`mistralai/mistral-medium-3.5-128b`	Free	Free	262K
evrocCheapest paid`mistralai/Mistral-Medium-3.5-128B`	$1.73	$6.90	262K
DevPass (LLM Gateway)`mistral-medium-3-5`	$1.50	$7.50	262K
Eden AI`mistral/mistral-medium-3-5`	$1.50	$7.50	262K
Kilo Gateway`mistralai/mistral-medium-3-5`	$1.50	$7.50	262K
LLM Gateway`mistral/mistral-medium-3-5`	$1.50	$7.50	262K
MistralOfficial`mistral-medium-2604`	$1.50	$7.50	262K
NanoGPT`mistralai/mistral-medium-3.5`	$1.50	$7.50	256K
OpenRouter`mistralai/mistral-medium-3-5`	$1.50	$7.50	262K

Show 9 more providers

Provider	Input	Output	Context
Pioneer`mistral-medium-3.5`	$1.50	$7.50	256K
Tempr Gateway`mistral/mistral-medium-2604`	$1.50	$7.50	262K
Vercel AI Gateway`mistral/mistral-medium-3.5`	$1.50	$7.50	262K
Cortecs`mistral-medium-3.5`	$1.53	$7.84	256K
LowRouter`auto/mistralai/mistral-medium-3.5`	$1.57	$7.84	262K
Requesty`mistral-medium-3-5`	$1.65	$8.25	262K
GreenPT`mistral-medium-3.5-128b`	$2.05	$10.26	262K
AI/ML API`mistralai/mistral-medium-3-5`	$2.06	$10.32	262K
SAP AI Core`mistralai--mistral-medium`	—	—	262K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.