Allen Institute for AI

Olmo 3 32B Think

Type
language model
Context
66K tokens
Max output
8K
Released
1 November 2025
API string
allenai/olmo-3-32b-think
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Kilo Code $0.15 $0.5 31 Jul 2026
OpenRouter $0.15 $0.5 31 Jul 2026
NanoGPT $0.3 $0.45 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 1,343.21 1,332–1,354 — —
Arena Score, programming 1,320.05 1,302–1,338 — —
Arena Score, mathematics 1,315.54 1,284–1,347 — —
Arena Score, hard prompts 1,302.5 1,291–1,314 — —
Arena Score, overall 1,298.78 1,291–1,307 — —
Arena Score, long queries 1,294.63 1,278–1,311 — —
Arena Score, multi-turn dialogue 1,290.21 1,269–1,312 — —
Arena Score, expert questions 1,286.68 1,249–1,324 — —
Arena Score, instruction following 1,275.63 1,260–1,291 — —
Arena Score in Russian 1,255.99 1,229–1,283 — —
Arena Score, creative writing 1,253.86 1,233–1,275 — —