chooseaimodel
← All models
Flashfastest and cheapest, lighter reasoningOpen Weights

Granite 4.2 8B Pricing

IBM Granite · ibm-granite-granite-4-2-8b

ShareXFacebookLinkedIn
Input / 1M tokens
$0.060
Output / 1M tokens
$0.250
Context window
131,072 tokens
175 pages of text
Max output
117,964 tokens

What it costs in practice

Estimate your own workloadOpens the calculator with Granite 4.2 8B preloaded — adjust volume and token counts there.

Price history

List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.

What it excels at

Cost-effective for high-volume text processing and long-context retrieval tasks; open weights enable self-hosted deployment with low per-token pricing.

The business tradeoff

8B scale limits complex reasoning depth and instruction following relative to larger models; output quality depends heavily on hosting configuration and fine-tuning.

Cheaper from IBM Granite

Same tier from other providers

Head-to-head

Vendor list rates, as of Sep 9, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.