Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
IBM
IBM
Efficient

Granite 3.1 2B Instruct

Nano

Smallest Granite 3.1, 2B for edge / mobile deployment with the same IBM indemnification surface.

Granite 3.1 2B Instruct is a efficient AI model from IBM. It costs $0.030 per million input tokens and $0.100 per million output tokens (blended $0.051/M), with a 128,000-token context window.

INPUT
$0.030/M
per million input tokens
OUTPUT
$0.100/M
per million output tokens
BLENDED 70/30
$0.051/M
unchanged since 3 May
CONTEXT
128,000
tokens
What it is good at
  • Edge / mobile
  • Apache 2.0
  • IBM indemnity on watsonx
Typical use cases
  • Edge inference in regulated industries
  • On-device assistants

Benchmarks

vs. best public score
MMLU55%
Multitask academic knowledge across 57 subjects.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from IBM

See all 5

Frequently asked questions

How much does Granite 3.1 2B Instruct cost?

Granite 3.1 2B Instruct costs $0.030 per million input tokens and $0.100 per million output tokens, for a blended reference rate of $0.051 per million tokens.

What is Granite 3.1 2B Instruct's context window?

Granite 3.1 2B Instruct supports up to 128,000 tokens of context in a single request.

What is Granite 3.1 2B Instruct best for?

Granite 3.1 2B Instruct is well suited to Edge / mobile, Apache 2.0 and IBM indemnity on watsonx.

Who makes Granite 3.1 2B Instruct?

Granite 3.1 2B Instruct is developed and served by IBM. It was released in Dec 2024.

Terms used on this page