← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Granite 4.2 8B Pricing
IBM Granite · ibm-granite-granite-4-2-8b
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
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.172/mo10,000 requests / month$1.72/mo100,000 requests / month$17.20/moEstimate 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
Head-to-head
Vendor list rates, as of Sep 9, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.