Claude Fable 5$22.000/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-5.5$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/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/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-5.5$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/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All IBM models
IBM
IBMEfficient

Granite Code 34B

Code

Code-tuned Granite. 34B model targeting enterprise code review and IP-safe code generation under IBM's indemnity.

Granite Code 34B is a efficient AI model from IBM. It costs $0.350 per million input tokens and $1.050 per million output tokens (blended $0.560/M), with a 8K-token context window.

Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.350/M
per million input tokens
OUTPUT
$1.050/M
per million output tokens
BLENDED 70/30
$0.560/M
default reference rate · how it's calculated →
CONTEXT
8K
8,000 tokens
What it's good at
  • Code-tuned
  • Apache 2.0 + IBM indemnity
  • Enterprise procurement-friendly
Typical use cases
  • Enterprise code review
  • IP-safe code generation
  • Regulated code workflows
Benchmarks
vs. best public score
HumanEval62%
Python function synthesis from docstrings.
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 →
Granite 3.1 8B Instruct
Compact · 128K ctx
in $0.050/Mout $0.250/M
Granite 3.1 2B Instruct
Nano · 128K ctx
in $0.030/Mout $0.100/M
Granite 3.0 8B Dense
Previous Gen · 4K ctx
in $0.050/Mout $0.250/M
Granite 20B Multilingual
Multilingual · 8K ctx
in $0.400/Mout $0.400/M
Frequently asked questions

How much does Granite Code 34B cost?

Granite Code 34B costs $0.350 per million input tokens and $1.050 per million output tokens, for a blended reference rate of $0.560 per million tokens.

What is Granite Code 34B's context window?

Granite Code 34B supports up to 8K tokens of context (8,000 tokens).

What is Granite Code 34B best for?

Granite Code 34B is well suited to Code-tuned, Apache 2.0 + IBM indemnity and Enterprise procurement-friendly.

Who makes Granite Code 34B?

Granite Code 34B is developed and served by IBM.