Mistral Nemo
Mistral AI · released Jul 17, 2024 · mistralai/Mistral-Nemo-Instruct-2407
- Type
- Open weightsApache License 2.0
- Params
- 12.2B
- Context
- 131K
about 98K words of context
Our take
Written Aug 3, 2026Mistral Nemo is a compact downloadable text model with a permissive Apache licence and a generous request limit for its size. Its academic scores are near the floor for modern models, so it is a budget utility pick rather than a quality leader.
Pick this for low-cost text inference where Apache licensing matters, or for long-context text tasks up to 131,072 tokens. Use it for local or self-hosted deployment with open weights. Skip it if you need strong reasoning or knowledge accuracy, or if you want measured chat or code quality.
The case for it
- Among the cheapest hosted inference we track at the low end.
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- 131,072-token request limit is large for a 12.2-billion-parameter model.
The case against it
- Weak academic benchmark performance: 28% on MMLU-Pro and 5.4% on GPQA Diamond, both near floor levels for modern models.
- Wide price spread with no throughput advantage at premium tiers: the vendor's own API charges several times more than the cheapest hosts for 48 tps, while DeepInfra offers 34 tps at the budget rate.
How good is it?
IntelligencePuzzles, maths, exam questions
Mistral Nemo is not on Arena Text (overall), which is where the rating would come from, so there is no rating here. It is on GPQA Diamond, in 12th of 16 with 5.4.
CodingWriting and fixing code on its own
Nobody we watch has scored Mistral Nemo for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Mistral Nemo for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 13.3 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 21.3 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Room to spare. 2.5 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 8 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.019 in / $0.030 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| DeepInfrafp8 | $0.019 / $0.030 | 131K | not measured | Unknown | Unknown | Unknown |
| DeepInfrafp8 | $0.019 / $0.030 | 131K | 34 tok/s | No | No | Confirmed |
| OpenRouter | $0.019 / $0.030 | 131K | not measured | Unknown | Unknown | Unknown |
| Parasailfp8 | $0.030 / $0.030 | 131K | 20 tok/s | No | No | Confirmed |
| Mistral AI | $0.15 / $0.15 | 131K | 48 tok/s | No | Yes30 days | Unknown |
| Io Netfp16 | $0.043 / $0.17 | 128K | 9 tok/s | No | No | Confirmed |
| Novita AIfp8 | $0.040 / $0.17 | 60K | 21 tok/s | No | No | Confirmed |
| Novita AI | $0.040 / $0.17 | 60K | not measured | Unknown | Unknown | Unknown |
DeepInfra
Mistral AI
Novita AIAcross the 8 listings we hold: 5 say they do not train on prompts, 0 say they do and 3 do not say. 4 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| DeepInfrafp8 | |||
| DeepInfrafp8 | ✗ | ✓ | ✗ |
| OpenRouter | ✓ | ✓ | ✓ |
| Parasailfp8 | ✗ | ✓ | ✓ |
| Mistral AI | ✓ | ✓ | ✓ |
| Io Netfp16 | ✓ | ✗ | ✗ |
| Novita AIfp8 | ✗ | ✓ | ✓ |
| Novita AI |
Tool calling: 3 of 8 listings say yes, 3 say no, 2 publish no parameter list. JSON output: 5 of 8 listings say yes, 1 says no, 2 publish no parameter list. Strict schema: 4 of 8 listings say yes, 2 say no, 2 publish no parameter list.
Models people weigh against Mistral Nemo
When we formed this view
Dates behind this page
Prices last checked 5d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- 2 of 8 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 3 of 8 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- mistralai/Mistral-Nemo-Instruct-2407
- Architecture
- Dense
- Modality record
- text->text
- Catalogue slug
- mistralai-mistral-nemo