Mistral Nemo
Mistral AIReleased Jul 18, 2024Open weights · Apache 2.0mistral-nemo
- Intelligence (Epoch)
- 119 · 108th of 111
- Reasoning
- no
- Context
- 131K tokens
- Max output
- 100k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
- Mistral AI's API
- yes, as open-mistral-nemo-2407
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Mistral AI
Intelligence for the price
On the best-deal line: no model scores higher for less than $0.038 per M.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 119 with an interval of 111 to 121.
Against its rivals
The best of its price range and the top score
- Mistral Nemothis model$0.038119
- Claude Opus 5.5top score$24.00169
- Llama 3.1 8Bsame price range$0.06116
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Speed by provider
Output speed of Mistral Nemo at each host, fastest first
- Mistral AI107 tok/s0.52 s to first token
- Io Net43 tok/s0.33 s to first token
- Parasail43 tok/s0.56 s to first token
- DeepInfra30 tok/s0.77 s to first token
- DekaLLM8 tok/s0.69 s to first token
Speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · a snapshot of real traffic before the daily read, not a daily average · bars from zero.
Run it yourself
open weights, Apache 2.0 · fits 6 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 12B
- dense
- Memory needed
- 7 GB
- in INT4 · 14 GB in INT8
- Smallest cloud setup
- RTX 3090
- 24 GB · $0.17/h, about $124 a month
- Worth it above
- 3B tokens
- a month, against the cheapest API at $0.038 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 7 GB | RTX 3090 · $0.17/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 14 GB | RTX 3090 · $0.17/h | near-lossless |
| FP16 (full) | 29 GB | A100 · $1.19/h | reference quality |
At home: in INT4 it fits a RTX 5090 (32 GB) + host PC (plus a host PC), about $3,500 once, or $0.1332/h over 3 years, electricity aside; it pays for itself after about 92B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Io Netfp16 · 125K ctx · 100K out−28% | $0.0166 | $0.0216 | $0.0108 | 43 | 0.33 s | 100% | Oct 23 |
| Mistral AI128K ctx · 105K out | $0.15 | $0.15 | $0.015 | 107 | 0.52 s | 100% | Oct 23 |
| DekaLLMfp8 (bf16) · 128K ctx · 105K out | $0.018 | $0.03 | — | 8 | 0.69 s | 100% | Oct 23 |
| DeepInfrafp8 (bf16) · 128K ctx · 16K out | $0.029 | $0.03 | — | 30 | 0.77 s | 100% | Oct 23 |
| Parasailfp8 (bf16) · 128K ctx · 105K out | $0.03 | $0.03 | — | 43 | 0.56 s | 100% | Oct 23 |
| Novita AIprecision not stated · 60K ctx (128K) · 16K out | $0.04 | $0.17 | — | — | — | — | Oct 8 |
6 of 6 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Io Net | fp16 | 125K | 100K | yes | no | no |
| DekaLLM | fp8 | 128K | 105K | no | yes | no |
| DeepInfra | fp8 | 128K | 16K | yes | yes | no |
| Parasail | fp8 | 128K | 105K | no | yes | no |
| Novita AI | not stated by the host | 60K | 16K | — | — | — |
| Mistral AI | not checked yet | 128K | 105K | yes | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Mistral Nemo spec sheet, field by field, with sources
Mistral Nemo spec sheetmaker-declared
What Mistral AI declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 131,072 tokens
- Parameters
- 12,247,782,400≈ 12.2B
- Active experts
- none declared in the weights
- Weight precision
- bfloat16
- License
- Apache 2.0 — open weights, permissivecurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the makermaker's docs · read 2026-09-07
- Modalities
- text
- Max output (official)
- to verify
- Release date
- July 18, 2024maker's docs · read 2026-09-07
- Maker lifecycle status
- Deprecated — retirement announced for May 22, 2026, still served until then · superseded by Ministral 3 8Bmaker's docs · read 2026-09-07
Also declared in the weights
- Architecture class
- MistralForCausalLM
- Layers
- 40
- Vocabulary
- 131,072 tokens
- Weights first published
- July 17, 2024
- Weights last updated
- July 28, 2025
- Languages declared
- 9 languages
mistralai/Mistral-Nemo-Instruct-2407 · config.json @ 04d8a90 · read 2026-10-08 · 7 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 13 | Io Net | $0.0184 → $0.0166 | $0.024 → $0.0216 | −10% |
| Oct 10 | Io Net | $0.0207 → $0.0184 | $0.027 → $0.024 | −11% |
| Oct 9 | DeepInfra | $0.019 → $0.029 | $0.03 → $0.03 | +20% |
| Oct 9 | Io Net | $0.023 → $0.0207 | $0.03 → $0.027 | −10% |
| Oct 7 | Io Net | $0.025 → $0.023 | $0.03 → $0.03 | −4% |
| Oct 6 | Io Net | $0.0321 → $0.025 | $0.12 → $0.03 | −63% |
| Oct 5 | Io Net | $0.0356 → $0.0321 | $0.13 → $0.12 | −10% |
| Sep 28 | Io Net | $0.0405 → $0.0356 | $0.15 → $0.13 | −12% |
| Sep 20 | Io Net | $0.044 → $0.0405 | $0.16 → $0.15 | −8% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Io Net | $0.03 | $0.14 | $0.09 |
| DekaLLM | $0.03 | $0.16 | $0.10 |
| DeepInfra | $0.04 | $0.25 | $0.15 |
| Parasail | $0.05 | $0.26 | $0.15 |
| Novita AI | $0.12 | $0.40 | $0.33 |
| Mistral AI | $0.23 | $1.28 | $0.75 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Mistral AI models · all its models, hosts and history ›
- Mistral Small 3.2 24B4 providers · from $0.28
- Mistral Small 42 providers · from $0.75
- Codestral 25081 provider · from $1.20
- Devstral 2 25121 provider · from $2.40
- Ministral 3 14B 25121 provider · from $0.40
- Ministral 3 3B 25121 provider · from $0.20