Granite 4.0 Micro

Open weight

IBM · Released October 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...

Facts and pricing

Provider
IBM
Context window
131K tokens
Input price
0.19 credits / 1M tokens ($0.017 raw)
Output price
1.2 credits / 1M tokens ($0.11 raw)
Vision (image input)
No
Tool calling
No
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Granite 4.0 Micro now

Ask Granite 4.0 Micro anything. Your prompt opens in the Zeplik app with this model selected.

Granite 4.0 Micro

What Granite 4.0 Micro is best for

IBM family

ModelContextInput cr/MOutput cr/MReleased
Granite 4.1 8B131K0.551.1April 2026
Granite 4.0 Micro131K0.191.2October 2025

Frequently asked questions

What is Granite 4.0 Micro?
Granite 4.0 Micro is an AI model by IBM. 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...
How much does Granite 4.0 Micro cost on Zeplik?
Input tokens cost 0.19 credits per million and output tokens 1.2 credits per million (1 credit = $0.10; the raw provider rates are $0.017 and $0.11 per million). New accounts start with free credits.
How long can a conversation with Granite 4.0 Micro be?
Granite 4.0 Micro has a 131K-token context window (131,000 tokens), which covers the conversation plus any documents you attach.
Does Granite 4.0 Micro support images and tools?
Granite 4.0 Micro is text-only and does not support tool calling.

Related models

Granite 4.1 8BOpen weight

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

131K ctx1.1 cr/M outApril 2026
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 Terra ProFrontier

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx165 cr/M outJuly 2026
GPT-5.6 TerraFrontier

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...

1.1M ctx165 cr/M outJuly 2026
GPT-5.6 Sol ProFrontier

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx330 cr/M outJuly 2026
Granite 4.0 Micro - IBM AI Model | Zeplik Chat