Mistral Nemo
Mistral · Released Jul 2024
Mistral Nemo is a compact language model from Mistral designed for efficient inference on resource-constrained environments.
- Strengths
- It delivers fast inference and low memory requirements while maintaining reasonable performance across general language tasks.
- Best for
- Latency-sensitive applications and deployments where computational resources or costs are limited.
- Limitations
- It sacrifices capability and nuance compared to larger Mistral models like Medium 3 or Large 2407, and is positioned below Ministral 8B in Mistral's lineup.
Input / 1M
$0.029
Output / 1M
$0.03
Cached input / 1M
—
Context window
131K
Price history
Input (solid)Output (dashed)
Price change
- 30d
- in increased 52.6% out decreased 0.0%
- 90d
- in increased 52.6% out decreased 0.0%
- 1y
- in increased 45.0% out decreased 0.0%
- Since launch
- in increased 45.0% out decreased 0.0%
Snapshots
| Effective | Input | Output | Cached in | Note | Source |
|---|---|---|---|---|---|
| 9 Oct 2026 | $0.029 | $0.03 | — | Imported from OpenRouter | openrouter.ai |
| 16 Jul 2026 | $0.019 | $0.03 | — | Imported from OpenRouter | openrouter.ai |
| 15 Jul 2026 | $0.02 | $0.04 | — | Imported from OpenRouter | openrouter.ai |
| 11 Jun 2026 | $0.02 | $0.03 | — | Imported from OpenRouter | openrouter.ai |