← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Granite 4.1 8B Pricing
IBM Granite · ibm-granite-granite-4-1-8b
Input / 1M tokens
$0.050
Output / 1M tokens
$0.100
Context window
131,072 tokens
≈ 175 pages of text
Max output
131,072 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0001
1,000 requests / month$0.1/mo10,000 requests / month$1.00/mo100,000 requests / month$10.00/moEstimate your own workloadOpens the calculator with Granite 4.1 8B preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Suitable for high-volume text classification, summarization, and simple instruction following when deployed via open weights. Low inference cost supports large-scale internal enterprise workloads.
The business tradeoff
8B scale produces noticeable gaps in multi-step reasoning and complex coding relative to 30B+ models. Output quality depends heavily on user fine-tuning and prompt engineering.
Cheaper from IBM Granite
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.