IBM

Granite 4.1 8B

Type
language model
Context
131K tokens
Max output
131K
Released
29 April 2026
API string
ibm-granite/granite-4.1-8b
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $0.05 $0.1 31 Jul 2026
NanoGPT $0.05 $0.1 31 Jul 2026
OpenRouter $0.05 $0.1 31 Jul 2026
Weights & Biases $0.05 $0.1 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score in English 1,317.1 1,303–1,331 — —
Arena Score, mathematics 1,316.17 1,277–1,355 — —
Arena Score, expert questions 1,311.43 1,279–1,344 — —
Arena Score, programming 1,311.15 1,291–1,331 — —
Arena Score, hard prompts 1,294.95 1,282–1,308 — —
Arena Score, overall 1,292.6 1,282–1,303 — —
Arena Score, long queries 1,276.57 1,260–1,293 — —
Arena Score, multi-turn dialogue 1,273.1 1,248–1,299 — —
Arena Score, instruction following 1,268.98 1,251–1,287 — —
Arena Score, creative writing 1,254.44 1,229–1,280 — —
Arena Score in Russian 1,251.47 1,221–1,282 — —
Arena Score, web development 1,193.98 1,175–1,213 — —