Context
20K
Max output
20K
Serving providers
1
Cheapest input
$0.06 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
WatsonxCheapest$0.06$0.251
ComponentUnitStandardBatchCached
Text input/1M tok$0.0600
Text output/1M tok$0.2500

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300Oct 17Jun 22$0.250$0.060

Cost calculator

estimate your monthly spend on this model
$32
estimated / month

Model IDs

copy the exact identifier for your platform
watsonx/ibm/granite-4-h-small

Frequently asked questions

Granite 4 H Small pricing, context and availability

How much does Granite 4 H Small cost?

Granite 4 H Small costs $0.06 per 1M input tokens and $0.25 per 1M output tokens at its cheapest provider via Watsonx.

What is the context window of Granite 4 H Small?

Granite 4 H Small accepts up to 20K tokens of context and can return up to 20K output tokens.

What can Granite 4 H Small do?

Granite 4 H Small supports tool use.

Other IBM models

compare pricing across the IBM lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI