Ibm: Granite-4.0-H-Small

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads

Model lab: Ibm
Model family: granite

Model resources

Hugging Face

Modalitiestext → text

Context window131,072

Maximum output131,072

InputUSD 0.05088 / 1M tokens

OutputUSD 0.212 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to ibm/granite-4-h-small.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "ibm/granite-4-h-small"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Granite-4.0-H-Small API Pricing

Type	Price information
Input	USD 0.05088 / 1M tokens
Output	USD 0.212 / 1M tokens

Performance

Performance trends

Throughput91.1 tok/sCurrent

Time to first token1.4 sCurrent

End-to-end latency7.0 sCurrent

Throughput

Current91.1 tok/s

Window average89.8 tok/s

Time to first token

Current1.4 s

Window average1.4 s

End-to-end latency

Current7.0 s

Window average7.5 s

Tail latency (P99)

Current17.4 s

Window average17.2 s

Prompt cache hit rate

Current31.4%

Window average22.5%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Granite-4.0-H-Small Compare models

Model	Input price	Output price	Context window	Capabilities
Granite-4.0-H-SmallThis page	USD 0.05088 / 1M tokens	USD 0.212 / 1M tokens	131,072	Text output · Tool calling
Granite 4.2 8B	USD 0.08 / 1M tokens	USD 0.12 / 1M tokens	131,072	Text output · Reasoning · Tool calling
Granite-4.0-H-Micro	USD 0.0136 / 1M tokens · Context ≤ 131000 tokens · Maximum output 131000 tokens	USD 0.0896 / 1M tokens · Context ≤ 131000 tokens · Maximum output 131000 tokens	131,072	Text output · Tool calling
Beam 1.0 501B A23B	USD 0.2 / 1M tokens	USD 0.8 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Ling 3.1 Flash	USD 0.06 / 1M tokens	USD 0.176 / 1M tokens	262,144	Text output · Reasoning · Tool calling

Model specifications

Input: text
Output: text
Context window: 131,072
Maximum output: 131,072
Release date: 2025-10-02
Attachments: No
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Granite-4.0-H-Small for?

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads

What inputs and outputs does Granite-4.0-H-Small support?

Recorded inputs: text; outputs: text.

How is Granite-4.0-H-Small priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.05088 / 1M tokens; Output USD 0.212 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Granite-4.0-H-Small?

Current model records list Context window 131,072 tokens; Maximum output 131,072 tokens.

What model parameter does the Quickstart use?

The example uses ibm/granite-4-h-small. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.