Granite 4.0 H Micro
by IBMChat
Efficient model for low-latency assistance, extraction, and routine automation
- Context
- 131K tokens
- Max output
- 131,000 tokens
- Parameters
- 3.2B total
- Released
- 2025-10-20
- Weights
- Open
- Licence
- apache-2.0
ibm/granite-4-0-h-micro · also seen as @cf/ibm-granite/granite-4.0-h-micro, ibm-granite/granite-4.0-h-micro
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-10-20
- Weights
- Opennot gated
- License
- apache-2.0
- Input
- Text
- Output
- Text
- Context window
- 131,000 max across endpoints
- Max output
- 131,000
- Providers
- 2 + 2 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.017–$0.0234 in · $0.112–$0.154 out per 1M tokens · across all 2 providers
More details
- Last updated
- 2025-10-20
- Knowledge cutoff
- Weights link
- Hugging Face · ibm-granite/granite-4.0-h-micro
- Parameters
- 3.2B total
- Developer country
- United States of America
- Training compute
- 3.2×10²³ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
No change since 19 Oct 2026. The cheapest direct price has been $0.017 in / $0.112 out per 1M tokens at Cloudflare Workers AI on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Granite 4.0 H Micro |
|---|---|---|---|---|---|
| Llama 3.2 3B InstructMeta | $0.0333 | $0.03 | $0.05 | 131K | +2% |
| Sarvam-30BSarvam AI | $0.0333 | $0.02 | $0.10 | 65.5K | +2% |
| GPT OSS 20BOpenAI | $0.03 | $0.018 | $0.09 | 131K | −9% cheaper |
| Mistral NemoMistral AI | $0.0292 | $0.029 | $0.03 | 131K | −11% cheaper |
| Nex-N2.5-MiniNex AGI | $0.0375 | $0.025 | $0.10 | 262K | +14% |
| Ling 3.0 FlashinclusionAI | $0.028 | $0.021 | $0.063 | 262K | −15% cheaper |
| Ministral 3BMistral AI | $0.04 | $0.04 | $0.04 | 131K | +22% |
| Voxtral Mini 3B 2507Mistral AI | $0.04 | $0.04 | $0.04 | — | +22% |
More from IBM
Newest IBM models in the catalogue. All IBM models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Granite 4.2 8B | 2026-08-31 | 131K | from $0.06 |
| granite-4-1-8b | 2026-04-29 | 131K | unpriced |
| Granite-4.0-H-Small | 2025-10-02 | 131K | from $0.0636 |
| granite-vision-3-2-2b | 2025-02-14 | 8.2K | from $0.10 |
| granite-3-3-8b-instruct | — | 8.2K | from $0.03 |
| granite-13b-chat-v2 | — | 8.2K | from $0.60 |
| granite-3-8b-instruct | — | 8.2K | from $0.20 |
| granite-ttm-512-96-r2 | — | 512 | from $0.38 |