Granite 4.0 Micro API

Granite 4.0 Micro on AIMLAPI.

Modalities
Image, TextText
Context window
131K tokens
Released
Oct 20, 2025
Status
Deprecated, shutdown on Oct 26, 2026

Granite 4.0 Micro overview

Granite 4.0 Micro was withdrawn on Oct 26, 2026

The model is no longer available on AI/ML API. See similar models that are available now.

Granite 4.0 Micro specs

Model ID
ibm-granite/granite-4.0-h-micro
Developer
Ibm Granite
Context window
131,000 tokens
Input
Image, Text
Output
Text
API
OpenAI-compatible, base URL https://api.aimlapi.com/v1

What is Granite 4.0 Micro API?

Where to Use Granite 4.0 Micro

Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.

Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.

Use cases

Granite 4.0 Micro is documented as suited to low-latency, edge, and local applications. It is also positioned as a building block for agentic workflows, where it can perform key tasks such as function calling quickly. It is documented for retrieval-augmented generation (RAG) use cases. It is also documented for multi-agent workflows and multi-tool agent automation.

Capabilities

  • Function calling
  • Reasoning
  • Streaming
  • Structured outputs
  • Web search

Granite 4.0 Micro benchmarks by Artificial Analysis

See how Granite 4.0 Micro scores on independent evaluations. Data retrieved Nov 4, 2026.

Benchmark results

Compare 16 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Related articles

All posts

Granite 4.0 Micro FAQ

What is the context window of Granite 4.0 Micro?

Granite 4.0 Micro has a 131,000 tokens context window and can return up to 131,000 tokens.

What inputs and outputs does Granite 4.0 Micro support?

Granite 4.0 Micro takes image, text as input and returns text.

What is the model ID for Granite 4.0 Micro?

Use ibm-granite/granite-4.0-h-micro as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does Granite 4.0 Micro cost?

Granite 4.0 Micro is priced at input $0.0233818 / 1M tokens, output $0.1540448 / 1M tokens.

Does Granite 4.0 Micro support streaming?

Yes, Granite 4.0 Micro can stream responses as they are generated.

Can Granite 4.0 Micro read images?

Yes, Granite 4.0 Micro accepts image input alongside text.

Is Granite 4.0 Micro a reasoning model?

Yes, it includes reasoning as a supported feature and capability.

Can Granite 4.0 Micro call external tools or functions?

Yes, it supports function calling along with parallel tool calls.

Start building with Granite 4.0 Micro