Mistral Nemo
nano-gpt/mistralai/mistral-nemo-instruct-2407 · family mistral-nemo · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.11
Blended $/1M (3:1)
$0.1003
Input $/1M
$0.1207
Output $/1M
$0.22
1M in + 1M out
$0.0502 −50%
Cache read $/1M
#972 of 7,322
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 16,384 tokens
- Max output
- 8,192 tokens
- Capabilities
- text
Same model, other providers
“Mistral Nemo” is offered by 8 providers — cheapest-effective first. Kilo Gateway is the cheapest at $0.02 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kilo Gateway | $0.019 | $0.03 | $0.02 | 131k |
| OpenRouter | $0.019 | $0.03 | $0.02 | 131k |
| Pioneer | $0.02 | $0.03 | $0.02 | 128k |
| NovitaAI | $0.04 | $0.17 | $0.07 | 60k |
| NanoGPT (this) | $0.1003 | $0.1207 | $0.11 | 16k |
| Vercel AI Gateway | $0.15 | $0.15 | $0.15 | 128k |
| Mistral | $0.15 | $0.15 | $0.15 | 128k |
| Helicone | $20 | $40 | $25.00 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"mistralai/mistral-nemo-instruct-2407","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):