IBM · Released Oct 2, 2025Granite-4.0-H-Small
Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads.
- Capability
- —No ECI score yet
- Input
- $0.064per 1M tokens
- Output
- $0.265per 1M tokens
- Context
- 131K131K max output
What it costs
- Input
- $0.064per million tokens
- Output
- $0.265per million tokens
- Blended (3:1)
- $0.114cheaper than 89% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.26 |
| Team assistant25M input + 5M output tokens | $2.92 |
| Production app250M input + 50M output tokens | $29.15 |
Official watsonx.ai API price, as listed on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Granite-4.0-H-Small yet.
The details
- Lab
- IBM
- Released
- Oct 2, 2025
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Inputs
- Text
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- API model ID
ibm/granite-4-h-smallon watsonx.ai- Availability
- 1 API providerlisted on models.dev
More from IBM
About Granite-4.0-H-Small
How much does Granite-4.0-H-Small cost?
Granite-4.0-H-Small costs $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). At a 3:1 input-to-output mix that is $0.114 per million tokens, cheaper than 89% of the 360 priced models we track.
What is the context window of Granite-4.0-H-Small?
Granite-4.0-H-Small accepts up to 131,072 tokens per request and can write up to 131,072 tokens in one response.
How good is Granite-4.0-H-Small?
Epoch AI has not published a Capabilities Index score for Granite-4.0-H-Small yet.
Is Granite-4.0-H-Small open source?
Yes. IBM publishes the weights, so it can be downloaded and self-hosted.
What inputs does Granite-4.0-H-Small support?
Granite-4.0-H-Small accepts text and replies in text. It is not a dedicated reasoning model, supports tool calling and can return structured JSON output.
When was Granite-4.0-H-Small released?
IBM released Granite-4.0-H-Small on Oct 2, 2025.
What are the best alternatives to Granite-4.0-H-Small?
The closest current models from other labs on capability, price and release date are Apertus 8B (Swiss AI, $0.10 / $0.20), Ministral 3 3B (Mistral AI, $0.10 / $0.10), Qwen Flash (Alibaba (Qwen), $0.05 / $0.40) and Sarvam 105B (Sarvam AI, $0.047 / $0.186).