All models · ibm-granite

IBM: Granite 4.0 Micro pricing and limits

id ibm-granite/granite-4.0-h-micro · listed 2025-10-20

Input (per 1M tokens)$0.017
Output (per 1M tokens)$0.112
Context window131,000 tokens
Max output117,900 tokens
Modalitiestext → text

What 1,000 calls cost at 1,000 input and 300 output tokens each: $0.05.

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...

Cheaper on both input and output, with at least half the context

ModelIn / 1MOut / 1MContext
Auto Router (Beta)$-1000000.000$-1000000.0002,000,000
Pareto Code Router$-1000000.000$-1000000.0002,000,000
Auto Router$-1000000.000$-1000000.0002,000,000
Thinking Machines: Inkling Small (free)freefree1,048,576
Thinking Machines: Inkling (free)freefree1,048,576
Google: Lyria 3 Pro Previewfreefree1,048,576

Other ibm-granite models

IBM: Granite 4.2 8B ($0.060 / $0.250)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=ibm-granite/granite-4.0-h-micro (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=ibm-granite. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with ibm-granite. Agent Exchange