Mistral NeMo Instruct: Benchmarks, Pricing & Context Window
Mistral NeMo Instruct is a language model from Mistral, released in July 2024, with a 131K-token context window, and pricing from $0.019/M input and $0.030/M output.
A state-of-the-art 12B multilingual model with a 128k context window, designed for global applications and strong in multiple languages.
Mistral NeMo Instruct benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Mistral NeMo Instruct across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Mistral NeMo Instruct holds up as conversations get longer.
Quality Tracker
Mistral NeMo Instruct Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Sep 10 2026Mistral NeMo Instruct pricing
Providers
Mistral NeMo Instruct starts at $0.0190 per million input tokens and $0.0300 per million output tokens via DeepInfra. See all 3 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0190 | — | $0.0300 | 131.1K/131.1K | — | — | / |
 Google | $0.150 | — | $0.150 | 128.0K/128.0K | 0.40 | — | / |
 Mistral AI | $0.150 | — | $0.150 | 128.0K/128.0K | 0.50 | — | / |
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 NeMo Instruct model size
Mistral NeMo Instruct has 12 billion parameters. See how it compares to other models in the same parameter range.
Mistral NeMo Instruct context window
Input and output token limits for Mistral NeMo Instruct, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Mistral NeMo Instruct.
Mistral NeMo Instruct latency
Mistral NeMo Instruct time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Mistral NeMo Instruct examples
Recent arena outputs from Mistral NeMo Instruct, picked from the highest-ranked matchups.
Mistral NeMo Instruct license
Mistral NeMo Instruct is released under the Apache 2.0 license, which permits commercial use, has 12.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 12.0B
Apache License 2.0 - allows commercial use
Mistral NeMo Instruct resources
Official sources for Mistral NeMo Instruct: provider documentation, official launch post, source repository.
Mistral NeMo Instruct vs other models
The most-compared alternatives to Mistral NeMo Instruct are Qwen2.5 32B Instruct, Phi 4 Mini, Granite 3.3 8B Base. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Mistral NeMo Instruct
Models ranked just above and below Mistral NeMo Instruct by LLM Stats score.
FAQ
Common questions about Mistral NeMo Instruct.