Mistral AI model product
Mistral NeMo
A state-of-the-art 12B multilingual model with a 128k context window, designed for global applications and strong in multiple languages.
Updated Aug 17, 2026. Default version: Mistral NeMo Instruct
LLMBoard Score0.0Mistral NeMo Instruct
Coverage40%7 benchmark families
Context window128KTokens
Official input price$0.15Mistral API
Mistral NeMo Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Mistral NeMo Benchmark Results
Benchmark scores for Mistral NeMo Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkCommonSenseQA | Score70.4% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkNatural Questions | Score31.2% | Rank02 | Participants7 | Percentile83.3% | EvidenceC | Evaluated |
| BenchmarkOpenBookQA | Score60.6% | Rank04 | Participants5 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkTriviaQA | Score73.8% | Rank11 | Participants18 | Percentile41.2% | EvidenceC | Evaluated |
| BenchmarkWinogrande | Score76.8% | Rank12 | Participants22 | Percentile47.6% | EvidenceC | Evaluated |
| BenchmarkHellaSwag | Score83.5% | Rank15 | Participants27 | Percentile46.1% | EvidenceC | Evaluated |
| BenchmarkTruthfulQA | Score50.3% | Rank18 | Participants18 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkMMLU | Score68.0% | Rank88 | Participants101 | Percentile13.0% | EvidenceC | Evaluated |
Mistral NeMo Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Mistral NeMo Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.15 input, $0.15 output per 1M
- Official provider
- Mistral
- Lowest third-party
- From $0.14 input, $0.14 output per 1M via OVHcloud AI Endpoints
- Tracked offerings
- 6
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOVHcloud AI Endpoints | Provider model IDmistral-nemo-instruct-2407 | Regionglobal | Input / 1M$0.14 | Output / 1M$0.14 | Context65.5K | Updated |
| ProviderCortecs | Provider model IDmistral-nemo-instruct-2407 | Regionglobal | Input / 1M$0.145 | Output / 1M$0.145 | Context128K | Updated |
| ProviderMistral | Provider model IDmistral-nemo | Regionglobal | Input / 1M$0.15 | Output / 1M$0.15 | Context128K | Updated |
| ProviderVercel AI Gateway | Provider model IDmistral/mistral-nemo | Regionglobal | Input / 1M$0.15 | Output / 1M$0.15 | Context128K | Updated |
| ProviderDigitalOcean | Provider model IDmistral-nemo-instruct-2407 | Regionglobal | Input / 1M$0.30 | Output / 1M$0.30 | Context128K | Updated |
| ProviderHelicone | Provider model IDmistral-nemo | Regionglobal | Input / 1M$20 | Output / 1M$40 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Mistral NeMo Runtime Performance
Provider-specific output speed and catalog latency for Mistral NeMo Instruct. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed42 tok/s | Catalog Latency0.4 s | Max Input128K | Max Output128K | Updated |
| ProviderMistral AI | Output Speed0.1 tok/s | Catalog Latency0.5 s | Max Input128K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Mistral NeMo Specifications
Technical details for the model's default version.
- Version
- Mistral NeMo Instruct
- Released
- Jul 18, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 12B
- Context window
- 128K
- Max output
- 128K
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Mistral NeMo Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMistral NeMo Instruct | Released | LLMBoard0.0 | Parameters12B | Context128K | Max output128K | Open weightsNo | LicenseApache 2.0 |
Mistral NeMo vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Mistral NeMo
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Shieldstral 1.0
Mistral AI
MA
Pixtral 12B
Mistral AI
MA
Ministral 8B
Mistral AI
MA
Codestral 22B
Mistral AI
MA
Mistral Large 2
Mistral AI
MA
Mistral Small 3 24B
Mistral AI
What is Mistral NeMo?
Key information about Mistral NeMo and its available data.
A state-of-the-art 12B multilingual model with a 128k context window, designed for global applications and strong in multiple languages.
Data as of 2026-08-17.
FAQ
Common questions about Mistral NeMo.
When was Mistral NeMo released?
Mistral NeMo's default version was released on Jul 18, 2024.
How much does Mistral NeMo cost?
Mistral NeMo's official API price is $0.15 per million input tokens and $0.15 per million output tokens via Mistral. The lowest tracked third-party offer starts at $0.14 input and $0.14 output via OVHcloud AI Endpoints.
Who created Mistral NeMo?
Mistral NeMo was created by Mistral AI.
What is the context window for Mistral NeMo?
The default version has a 128K token context window.
Is Mistral NeMo open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Mistral NeMo?
6 provider offerings are linked to the default version.
What models should I compare Mistral NeMo with?
Nearby ranked alternatives include Codestral 22B, DeepSeek-VL2, Gemma 3n E2B.