Mistral
Mistral Nemo
Released 2024-07-19 · Knowledge up to 2024-04-30
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
You send / 1M
$0.029
tokens in
It replies / 1M
$0.030
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0001
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Io Net · fp16 | $0.017 | $0.022 | 100% | Read |
| DekaLLM · fp8 | $0.018 | $0.030 | 100% | Read |
| Parasail · fp8 | $0.030 | $0.030 | 99% | Read |
| DeepInfra · fp8 | $0.029 | $0.030 | 100% | Read |
| Mistral | $0.150 | $0.150 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 16K tokens
Similar models
- Llama 3.1 8B InstructMeta · $0.020 in / $0.040 out per 1M
- Llama 3 8B LunarisSao10k · $0.040 in / $0.050 out per 1M
- Mistral Small 3Mistral · $0.050 in / $0.080 out per 1M
- MythoMax 13BGryphe · $0.080 in / $0.110 out per 1M
- Phi 4Microsoft · $0.070 in / $0.140 out per 1M
- Nova Micro 1.0Amazon · $0.035 in / $0.140 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models