Granite 3.3 8B Instruct is IBM's language model with a 8K context window and up to 8K output tokens, available from 2 providers, starting at $0.030 / 1M input and $0.200 / 1M output. IBM's 8B-parameter Granite 3.3 instruction model offering improved reasoning and enterprise task performance in a mid-size open-weight package.
Specifications
Canonical IDibm-granite-3-3-8b-instruct
TypeLanguage
StatusActive
CreatorIBMIBM
Providers
Context Window8K tokens
Max Output8K tokens
Input ModalitiesText
Output ModalitiesText
Parameters8B
Benchmarks
Intelligence Index
7.0
#455
Coding Index
3.4
#358
Math Index
6.7
#233
MMLU-Pro
0.5
#282
GPQA
0.3
#388
HLE
0.0
#367
LiveCodeBench
0.1
#280
AIME
0.0
#141
IFBench
0.2
#369
Time to First Token
21.77s
#460
SciCode
0.1
#393
MATH-500
0.7
#136
AIME 2025
0.1
#233
LCR
0.0
#317
TerminalBench Hard
0.0
#352
TAU2
0.1
#351
Output TPS

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Granite 4.1 8B131K$0.050$0.100Available
Granite 4 Micro H131K$0.017$0.112Available
Granite 4.1 30BAvailable
Granite 4 Small H20K$0.060$0.250Available
Granite 4.1 3BAvailable
Granite 4 Nano 1B HAvailable
Granite 4 MicroAvailable
Granite 4 Nano 1BAvailable
Granite 4 350MAvailable
Granite 4 350M HAvailable
Granite 3.3 8B Instruct8K$0.030$0.200Current

Model IDs