Host Io Net cut Mistral Nemo pricing by 8%
Published 20 September 2026
Price move, per 1M tokens
- Io Net · input↓ 8%$0.0440 → $0.0405
- Io Net · output↓ 8%$0.160 → $0.147
- Io Net · cache read↓ 8%$0.0290 → $0.0267
| host | rate | was | now | change |
|---|---|---|---|---|
| Io Net | input | $0.0440 | $0.0405 | ↓ 8% |
| Io Net | output | $0.160 | $0.147 | ↓ 8% |
| Io Net | cache read | $0.0290 | $0.0267 | ↓ 8% |
all rates: ↓ 8%
If you buy
a lower meter on this host makes Mistral Nemo easier to keep in a high-volume loop, so re-check your spend cap and whether cached reads still cover your prompt pattern.
The model
Mistral Nemoopen the model →
Open weights12.2B parameters131K context9 hosts
No leaderboard with a large enough field rates this model yet.
Mistral Nemo is a 12.2-billion-parameter text model released in 2024 with a permissive Apache licence. It offers a 131,072-token request limit and some of the cheapest hosted inference among open-weights models we track, though its reasoning scores are near the floor for measured models.
Source
Read on openrouter.ai · we published this on 20 September 2026.
read the original at openrouter.ai ↗