Granite 4.0 Micro
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 context tool calling.
- Input / output price
- $0.017 / $0.112 per 1M
- Context
- 131K tokens
- Released
- Oct 2, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/ibm-granite-micro | $0.017/M | $0.112/M |
Pricing
USD per 1M tokens on Concentrate, after gateway discounts.
- Input
- $0.017 per 1M
- Output
- $0.112 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better13tokens/sacross providers
Response latency
Lower is better2.4sacross providers
Benchmarks
7 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| HumanEvalhuggingface.co | 81% | huggingface.co | Oct 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 57.6% | huggingface.co | Oct 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQAhuggingface.co | 32.1% | huggingface.co | Oct 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GSM8Khuggingface.co | 81.3% | huggingface.co | Oct 2, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalhuggingface.co | 84.3% | huggingface.co | Oct 2, 2025 |
| MMLUhuggingface.co | 67.4% | huggingface.co | Oct 2, 2025 |
| MMLU-Prohuggingface.co | 43.5% | huggingface.co | Oct 2, 2025 |
Apps
Use Granite 4.0 Micro in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Granite 4.0 Micro FAQ
Short answers, built from the data on this page.
Granite 4.0 Micro is a model from IBM, released on Oct 2, 2025. 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 context tool calling.
On the Respan gateway, Granite 4.0 Micro costs $0.017 per 1M input tokens and $0.112 per 1M output tokens on Concentrate, after gateway discounts.
Granite 4.0 Micro is served by Concentrate.
Granite 4.0 Micro accepts up to 131K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "granite-4.0-h-micro". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Granite 4.0 Micro has 7 published benchmark scores, including HumanEval 81%, BFCL-v3 57.6%, and GPQA 32.1%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.