Granite 4.0 Micro
openrouter The API that serves this model and sets the prices shown here. ibm-granite/granite-4.0-h-micro The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Micro Small enough to run on a phone, laptop or other edge device.Provider: ibm · served via OpenRouter
Nothing to act on today. The cost is the checking: someone has to remember to look again next month, and the month after. Coolhand watches this model for you and automatically updates your agents to the most compatible replacement the moment a retirement is announced — one less thing on your list, permanently.
Sticker prices & cost-per-token
List rates as published by OpenRouter, before any volume or enterprise discounts.
$0.017
$0.112
131,000 tokens
117,900
tokens per response (includes reasoning tokens)
Open weights (permissive license)
Apache-2.0
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=ibm-granite%2Fgranite-4.0-h-micro&q%5Bsource_api_eq%5D=openrouter"Pricing History
| Effective | Price |
|---|---|
| Aug 16, 2026 – present | Input cost: $0.017 / 1M, Output cost: $0.112 / 1M, Cached input cost: $0.00 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
No automated scan changes recorded yet.
| Date | Changed by | What changed |
|---|---|---|
| Aug 16, 2026 | Unknown | Initial record created |
Source
https://models.dev/api.json (models.dev provider 'openrouter', bulk import 2026-08-13)Comparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
Granite 4.0 Micro (ibm via OpenRouter) costs $0.017 per 1M input tokens and $0.112 per 1M output tokens, as last published by OpenRouter.
Granite 4.0 Micro has a context window of 131,000 tokens (the maximum combined input and output it can handle in a single request).
Granite 4.0 Micro sits in the micro size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
Granite 4.0 Micro can generate up to 117,900 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
Granite 4.0 Micro accepts text as input and produces text as output, as recorded in the Coolhand catalog.
Yes — the weights of Granite 4.0 Micro can be downloaded under the Apache-2.0 license. Check the license terms for any limits on commercial use.
No, Granite 4.0 Micro is currently active with no announced deprecation date.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=openrouter&q[model_eq]=ibm-granite%2Fgranite-4.0-h-micro — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks Granite 4.1 8B from ibm. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| Granite 4.1 8B via OpenRouter | $0.05/1M $0.0000000500 | $0.10/1M $0.0000001000 | — | — | Active |
Track LLM pricing and deprecations automatically.
Start free