Granite 3.2 8B API Pricing
Open-weight · 128K context · Available from 7 hosts. Cheapest: Novita at $0.08 input / $0.08 output per 1M tokens.
Granite 3.2 8B price by host (7 providers)
| Host | Input /1M | Output /1M | In+Out |
|---|---|---|---|
| Novita | $0.08 | $0.08 | $0.16 |
| DeepInfra | $0.085 | $0.085 | $0.17 |
| Groq | $0.095 | $0.095 | $0.19 |
| IBM | $0.1 | $0.1 | $0.2 |
| Together | $0.1 | $0.1 | $0.2 |
| OpenRouter | $0.1 | $0.1 | $0.2 |
| Fireworks | $0.105 | $0.105 | $0.21 |
Prices per 1M tokens, USD. Snapshot 2026-07 — verify with the provider before relying on them.
Granite 3.2 8B cost calculator
Frequently asked
How much does Granite 3.2 8B cost per 1M tokens?
Granite 3.2 8B costs $0.08 per 1M input tokens and $0.08 per 1M output tokens at its cheapest host (Novita).
What is Granite 3.2 8B's context window?
Granite 3.2 8B supports a context window of about 128K tokens. Remember every token in the context is billed on each call.
Where is Granite 3.2 8B cheapest to run?
Across 7 hosts, Novita is currently cheapest at $0.08/$0.08 per 1M tokens, versus Fireworks at $0.105/$0.105. Prices change often — use the comparison table above.