Mistral Medium 3.5: Benchmarks, Pricing & Context Window
Mistral Medium 3.5 is a language model from Mistral, released in April 2026, with multimodal input, a 256K-token context window, and pricing from $1.50/M input and $7.50/M output.
Mistral Medium 3.5 is Mistral AI's first flagship merged model: a dense 128B-parameter multimodal model with a 256k context window that unifies instruction-following, reasoning, and coding capabilities in a single set of weights. It
Mistral Medium 3.5 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Mistral Medium 3.5 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Mistral Medium 3.5 holds up as conversations get longer.
Quality Tracker
Mistral Medium 3.5 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 02 2026Mistral Medium 3.5 pricing
Providers
Mistral Medium 3.5 starts at $1.50 per million input tokens and $7.50 per million output tokens via Mistral AI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Mistral AI | $1.50 | — | $7.50 | 256.0K/256.0K | 26.95 | 325 | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Mistral Medium 3.5 model size
Mistral Medium 3.5 has 128 billion parameters. See how it compares to other models in the same parameter range.
Mistral Medium 3.5 context window
Input and output token limits for Mistral Medium 3.5, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Mistral Medium 3.5.
Mistral Medium 3.5 latency
Mistral Medium 3.5 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live model usage
Mistral Medium 3.5 examples
Recent arena outputs from Mistral Medium 3.5, picked from the highest-ranked matchups.
Mistral Medium 3.5 license
Mistral Medium 3.5 is released under the Modified MIT License license, which restricts commercial use, has 128.0B parameters.
- License
- Modified MIT License
- Non-commercial
- Parameters
- 128.0B
Mistral Medium 3.5 resources
Official sources for Mistral Medium 3.5: provider documentation, official playground, official launch post, model weights.
Mistral Medium 3.5 vs other models
The most-compared alternatives to Mistral Medium 3.5 are GPT OSS 120B High, Ministral 3 (14B Reasoning 2512), Grok 4 Fast. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Mistral Medium 3.5
Models ranked just above and below Mistral Medium 3.5 by LLM Stats score.
FAQ
Common questions about Mistral Medium 3.5.