impulse

Granite 4.0 H Micro

Open weights
API id granite-4.0-h-micro
Input / 1M
$0.017
at Cloudflare Workers AI
Output / 1M
$0.112
at Cloudflare Workers AI
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Cloudflare Workers AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.017$0.112

What it costs a month

At Cloudflare Workers AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$13.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$12.19
  • Coding agent1,000 requests a day, 40K in / 2K out$27.12
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$67.68
Use your own numbers

Where to run it

1 host serve Granite 4.0 H Micro. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
granite-4.0-h-micro
$0.017 / $0.112

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Cloudflare Workers AI.

Smaller IBM models

No cheaper IBM model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Ministral 3B
    Mistral AI · on Azure AI Foundry
    $0.04 / $0.04
    Has every key capability
    2% less
  • Gemma 4 E4B IT
    Google · on DeepInfra
    $0.02 / $0.10
    Has every key capability
    2% less
  • Llama 3.1 8B
    Meta · on LlamaGate
    $0.03 / $0.05
    Has every key capability
    14% less
  • gpt-oss-20b
    OpenAI · on Darkbloom
    $0.0145 / $0.07
    Has every key capability
    30% less

Call it

Using Cloudflare Workers AI's API.

Python
from litellm import completion

response = completion(
    model="cloudflare/granite-4.0-h-micro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Granite 4.0 H Micro cost?

On Cloudflare Workers AI, Granite 4.0 H Micro costs $0.017 per million input tokens and $0.112 per million output tokens.

Which APIs offer Granite 4.0 H Micro?

Granite 4.0 H Micro runs on 1 API: Cloudflare Workers AI.

What is Granite 4.0 H Micro's context window?

131K tokens, with up to 131K tokens in one reply.

Is Granite 4.0 H Micro being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Granite 4.0 H Micro?

Models that cost less and keep most of what it can do: Ministral 3B on Azure AI Foundry (2% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Granite 4.0 H Micro's API model id?

Use granite-4.0-h-micro with Cloudflare Workers AI.

Sources

Raw catalog entry for granite-4.0-h-micro on Cloudflare Workers AI
{
  "input_cost_per_token": 1.7e-8,
  "litellm_provider": "cloudflare",
  "max_input_tokens": 131000,
  "max_output_tokens": 131000,
  "mode": "chat",
  "output_cost_per_token": 1.12e-7,
  "rpm": 300,
  "supports_function_calling": true
}