About
Olmo 3.1 32B Instruct is a large-scale, 32-billion-parameter instruction-tuned language model engineered for high-performance conversational AI, multi-turn dialogue, and practical instruction following. As part of the Olmo 3.1 family, this...
Related Models
Pricing
Input
$0.20
per 1M tokens
Output
$0.60
per 1M tokens
Blended
$0.30
per 1M tokens
Cheaper than 62% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.30
Monthly
$9.00
vs. Similar Models
Sarvam 30B (high)Q:+0.1
$0.05-84%
AllenAI: Olmo 3 32B ThinkQ:-0.1
$0.24-21%
Mistral: SabaQ:-0.1
$0.300%
IBM: Granite 4.1 8BQ:+0.2
$0.06-79%
Performance
54
tokens/sec
Faster than 24% of models
0.29
seconds
Faster than 97% of models
0.29
seconds
Faster than 99% of models
Market Median
94 tok/s
42% slower
Median TTFT
1.10s
74% faster
Throughput/Dollar
181
tok/s per $/1M
Speed Comparison
Anthropic: Claude Opus 4.7
54 tok/s-1%
Gemma 3 1B Instruct
55 tok/s+1%
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
55 tok/s+1%
Context Window
66K
tokens
Larger than 13% of models
Max Output
16K
tokens
25% of context
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
53.9%
HLE
4.9%
LiveCodeBenchNot evaluated
SciCode
16.7%
TerminalBench Hard
0.0%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
39.2%
Long Context Recall
0.0%
Tau2
21.3%
Market AverageTop Score