One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $1.50 = $1.50
- Output0.1M x $7.50 = $0.75
$2.25per session
Mistral AI - Open weights
Mistral Medium 3.5 pricing and specs
Mistral Medium 3.5 is an open-weights model from Mistral AI that costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on the first-party API, with a 256K-token context window.
Last verified from docs.mistral.ai. All sources
- Input / 1M
- $1.50
- Output / 1M
- $7.50
- Context
- 256K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $1.50 |
| Output | $7.50 |
| Cache read | $0.15 |
| Batch inputBatch requests | $0.75 |
| Batch outputBatch requests | $3.75 |
Note: Batch prices come from the pricing page's Batch mode, which applies a factor of 0.5 to standard prices. Priority Tier adds 75% and regional inference adds 10%. The docs and weights card give the context only as '256k', and the Vercel AI Gateway lists 262144. No primary page states a max output. The weights license is a Modified MIT license, open for commercial use with exceptions for companies with large revenue. The model card is dated April 28, 2026; release date uses the changelog date (April 27). The gateway names this id 'Mistral Medium Latest'.
Specs
- Context window
- 256,000 tokens
- Release date
- Provider
- Mistral AI
- API model id
mistral-medium-3-5- Vercel AI Gateway id
mistral/mistral-medium-3.5- Weights
- Open weights
- License
- Modified MIT (https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE)
- Weights download
- huggingface.co
What Mistral Medium 3.5 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $1.50 = $30.00
- Output5M x $7.50 = $37.50
$67.50per day
$2,025.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.15 = $0.135
- Uncached input0.1M x $1.50 = $0.15
- Output0.1M x $7.50 = $0.75
$1.04per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Mistral Medium 3.5 (this page) | $1.50 | $7.50 |
| Qwen3.7-MaxAlibaba Cloud (Qwen) | $2.50 | $7.50 |
| GPT-4.1OpenAI | $2 | $8 |
| Jamba Large 1.7AI21 Labs | $2 | $8 |
| Kimi K2.7 Code HighSpeedMoonshot AI | $1.90 | $8 |
| Mistral Large 4Mistral AI | $1.36 | $4.18 |
| Mistral Large 3Mistral AI | $0.50 | $1.50 |
| Codestral 25.08Mistral AI | $0.30 | $0.90 |
| Mistral Small 4Mistral AI | $0.15 | $0.60 |
| Ministral 3 14BMistral AI | $0.20 | $0.20 |
| Ministral 3 8BMistral AI | $0.15 | $0.15 |
Compare
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
- Mistral Medium 3.5 vs Gemini 3.8 FlashSimilar price, same tier
- Mistral Medium 3.5 vs GLM-5.3Similar price, same tier
- Mistral Medium 3.5 vs Grok Build 0.1Similar price, same tier
- Mistral Medium 3.5 vs DeepSeek V4 ProSimilar price, same tier
- Mistral Medium 3.5 vs GPT-5.4 MiniSimilar price, same tier
- Mistral Medium 3.5 vs Kimi K2.7 CodeSimilar price, same tier
Related reading
- Mistral Large 4: Specs, Pricing, Benchmarks and Weights DateMistral Large 4 is a 1T-parameter multimodal MoE with 52B active, in public preview at $0.68/$2.09 per million tokens, with open weights due end of October.
- Mistral Shieldstral: A 3B Open-Weight Policy-Adaptive Moderation Model That Beats Models 7x Its SizeMistral Shieldstral is a 3B Apache 2.0 multimodal moderation model that takes your policy as a plain-language question at inference and runs on one 16GB GPU.
- Mistral Releases Robostral Navigate: An 8B Robotics Navigation ModelMistral Robostral Navigate is an 8B robotics model that navigates with only a camera and natural language commands. How it works and what the benchmarks mean.
- Leanstral 1.5: Mistral's Open Theorem-Proving Model Hits 100% on miniF2FLeanstral 1.5 is Mistral's open Apache-2.0 model for Lean 4 theorem proving. The benchmark claims, the HN pushback on its bug-finding pitch, and how to use it.
- Mistral OCR 4 and Unlimited OCR Make Document Parsing an Agent Runtime ChoiceMistral OCR 4 and Baidu's Unlimited OCR turn document parsing into a runtime choice for agents - cost per page, layout, confidence scores and self-hosting.
- Codex Custom Model Providers: GLM-5.3, Mistral and OllamaCodex only speaks the Responses API now. Tested config.toml blocks for GLM-5.3, Mistral Large 4 through a gateway, local Ollama and an internal proxy.
FAQ
How much does Mistral Medium 3.5 cost per million tokens?
Mistral Medium 3.5 costs $1.50 per 1M input tokens and $7.50 per 1M output tokens on Mistral AI's first-party API, per docs.mistral.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.15, and the batch rate is $0.75 input and $3.75 output.
What is Mistral Medium 3.5's context window?
Mistral Medium 3.5 has a 256,000-token context window.
Are Mistral Medium 3.5's weights open?
Yes. Mistral Medium 3.5's weights are published at https://huggingface.co/mistralai/Mistral-Medium-3.5-128B under the Modified MIT (https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE).
When was Mistral Medium 3.5 released?
Mistral AI released Mistral Medium 3.5 on April 27, 2026.
Sources
Last verified from docs.mistral.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.