IBM
Granite 4.0 Micro
Efficient model for low-latency assistance, extraction, and routine automation
Model facts
- Context window
- 131K tokens
- Maximum output
- 118K tokens
- Cheapest paid input
- $0.017 per 1M tokens
- Cheapest paid output
- $0.112 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
temperature control, open weights, text.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 2.0 | not measured | 6.0 | not measured |
Observed price history
- 2026-08-24: $0.017 input / $0.112 output per 1M tokens
API providers
- Kilo Gateway (IBM) — model id ibm-granite/granite-4.0-h-micro; $0.017 input / $0.112 output per 1M tokens; provider documentation
- OpenRouter — model id ibm-granite/granite-4.0-h-micro; $0.017 input / $0.112 output per 1M tokens; provider documentation