IBM · live price
Granite 4.0 Micro API pricing
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...
- Input
- $0.017
- per 1M tokens
- Output
- $0.112
- per 1M tokens
- Cached input
- –
- per 1M tokens
- Context
- 131K
- 118K max output
List price from OpenRouter, which passes IBM's price through without markup. Refreshed hourly. Released October 20, 2025. Model id ibm-granite/granite-4.0-h-micro.
What Granite 4.0 Micro costs in practice
1,000 chat messages
$0.07
1,000 input + 500 output tokens each
1,000 RAG questions
$0.19
8,000 input + 500 output tokens each
100 coding-agent steps
$0.07
30,000 input + 2,000 output tokens each, no caching
Granite 4.0 Micro price history
Granite 4.0 Micro price by host
- Cloudflare$0.017 in · $0.112 out · 131K ctx · 100.0% uptime 24h
Where to buy IBM credits for less
Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare
Granite 4.0 Micro cost calculator
Cheaper alternatives to Granite 4.0 Micro
| Model | Input / 1M | Output / 1M |
|---|---|---|
| OpenAI: gpt-oss-20b | $0.018 | $0.09 |
| Mistral: Mistral Nemo | $0.019 | $0.03 |
| inclusionAI: Ling 3.0 Flash VL | $0.021 | $0.062 |
| inclusionAI: Ling 3.0 Flash | $0.021 | $0.063 |
Other IBM models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Granite 4.2 8B | $0.06 | $0.25 |