Jahanzaib

IBM models

IBM has 3 models in the directory. The newest is Granite 4.2 8B, released Aug 24, 2026.

The cheapest to run is Granite 4.0 H Micro at $0.017 per million input tokens.

Granite 4.2 8B has the longest context window, 131K tokens.

Models
3
Newest
Aug 24, 2026
From
$0.017/M input
Longest context
131K

All IBM models

Filter in the directory

  • Granite 4.2 8B

    Reads text. Tool calling, structured output, reasoning. Served by 4 providers.

    by ibm-graniteAug 24, 2026$0.10/M input tokens$0.15/M output tokens4 providers

  • Granite-4.0-H-Small

    Reads text. Tool calling, structured output.

    by ibm-graniteOct 2, 2025$0.0636/M input tokens$0.265/M output tokens

  • Granite 4.0 H Micro

    Reads text. Tool calling, structured output. Served by 3 providers.

    by ibm-graniteOct 2, 2025$0.017/M input tokens$0.112/M output tokens3 providers

Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.

Not sure which IBM model fits?

I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.

Book Meeting