IBM Granite
IBM 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 window
- 131Ktokens
- Max output
- 118Ktokens
- Input
- $0.017/ 1M
- Output
- $0.112/ 1M
Quick start
from openai import OpenAI
client = OpenAI(
base_url="https://neurongate.net/v1",
api_key="sk-ng-your-api-key",
)
completion = client.chat.completions.create(
model="ibm-granite/granite-4.0-h-micro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(completion.choices[0].message.content)Cost
| Example request | Tokens | Cost |
|---|---|---|
| Short prompt | 1K in | $0.000017 |
| Typical chat turn | 1K in · 500 out | $0.000073 |
| Document analysis | 10K in · 2K out | $0.000394 |
| Long context | 100K in · 10K out | $0.00282 |
Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.
Frequently asked questions
What is IBM 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...
How much does IBM Granite 4.0 Micro cost?
IBM Granite 4.0 Micro is priced at $0.017 per 1 million input tokens and $0.112 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).
Does IBM Granite 4.0 Micro support streaming?
Yes, IBM Granite 4.0 Micro supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.
What is the context window of IBM Granite 4.0 Micro?
IBM Granite 4.0 Micro has a context window of 131K tokens (~98K words). Maximum output is 118K tokens.
Does IBM Granite 4.0 Micro support function calling (tools)?
IBM Granite 4.0 Micro does not currently support function calling / tool use.
How do I use IBM Granite 4.0 Micro with NeuronGate?
Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id ibm-granite/granite-4.0-h-micro in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.