Mistral Nemo
Mistral NemoRankingconfiguration unstated?
Alternatives?
CheaperGPT OSS 20BmediumOpen+63%-76%$0.018 / $0.09Memory (4-bit): 6.1 GB → 13 GB
BetterGemini 3.1 Prounstated×2+2,900%$2 / $12CheaperGemma 2 9B ItOpen+16%-75%$0.03 / $0.06Context: 131K → 8K
CheaperQwen 2 7B InstructOpen+5%-63%$0.055 / $0.055Context: 131K → 33K
CheaperLlama 3.1 8B InstructunstatedOpensame-83%$0.02 / $0.04GPT OSS 20BmediumOpen+63%-76%$0.018 / $0.09Memory (4-bit): 6.1 GB → 13 GBGemma 2 9B ItOpen+16%-75%$0.03 / $0.06Context: 131K → 8KQwen 2 7B InstructOpen+5%-63%$0.055 / $0.055Context: 131K → 33KLlama 3.1 8B InstructunstatedOpensame-83%$0.02 / $0.04Gemini 3.1 Prounstated×2+2,900%$2 / $12GPT-4ounstated+67%+2,817%$2.50 / $10Context: 131K → 128KGPT OSS 20BmediumOpen+63%-76%$0.018 / $0.09Memory (4-bit): 6.1 GB → 13 GBQwQ 32BOpen+54%+42%$0.15 / $0.40Memory (4-bit): 6.1 GB → 20 GBLlama 3.3 70B InstructunstatedOpen+47%+3%$0.10 / $0.32Context: 131K → 128K+1GPT OSS 20BmediumOpen+63%-76%$0.018 / $0.09Memory (4-bit): 6.1 GB → 13 GBGemma 2 27BunstatedOpen+26%+80%$0.27 / $0.27Context: 131K → 8K+1Gemma 2 9B ItOpen+16%-75%$0.03 / $0.06Context: 131K → 8K
Phi 3.5 Mini InstructOpen+7%——Qwen 2 7B InstructOpen+5%-63%$0.055 / $0.055Context: 131K → 33KMixtral 8x22B InstructunstatedOpen+26%—$2 / $6Context: 131K → 66K+1Mixtral 8x7B Instruct v0.1Open-3%—$0.54 / $0.54Context: 131K → 33K+1Mistral 7B v0.1Open-31%—$0.40 / $0.80Context: 131K → 33KMistral 7B Instruct v0.2Open-31%—$0.055 / $0.055Context: 131K → 33K+1Mistral 7B Instruct v0.1Open-43%—$0.055 / $0.055Context: 131K → 33KMistral Large 4thinkingn/a—$1.13Infinite whitespace stream+4Mistral Medium 3.5highOpenn/a—$0.50Memory (4-bit): 6.1 GB → 77 GBMistral Small 4thinkingOpenn/a—$0.015Memory (4-bit): 6.1 GB → 72 GBAll Mistral models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does Mistral Nemo cost?›
$0.15 per 1M input tokens and $0.15 per 1M output tokens; cached input $0.015 per 1M; cheapest via DekaLLM at $0.018 / $0.03.
Is Mistral Nemo free to use?›
There is no free API; the cheapest paid price is $0.018 per 1M input tokens. The weights are open, so you can run it yourself.
How good is Mistral Nemo, and what is it best at?›
#20 of 32 in Chat & Knowledge, #91 of 95 in Writing & Language.
Is Mistral Nemo better than EXAONE 3.5 7.8B Instruct?›
On MMLU-Pro · official board, Mistral Nemo scores 44.8 vs 46.2 — lower.
How can I use Mistral Nemo?›
Through the API of DeepInfra, DekaLLM, Mistral, Parasail.
What is the context window of Mistral Nemo?›
131K tokens, with up to 105K output tokens.
When was Mistral Nemo released? Is there a newer version?›
Released 2024-07-01. It is the current version in its line.
Is Mistral Nemo open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Mistral Nemo locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Mistral Nemo read images?›
No, it accepts text only.
What is Mistral Nemo?›
Mistral Nemo is an open-weights language model from Mistral, released Jul 2024.
What are the best alternatives to Mistral Nemo?›
GPT OSS 20B (cheaper), Gemini 3.1 Pro (better).