Granite 3.3 8B
Granite 3.3 8B 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. An 8B-parameter IBM Granite 3.3 instruction-tuned model designed for enterprise NLP tasks with multilingual and reasoning capabilities.
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. An 8B-parameter IBM Granite 3.3 instruction-tuned model designed for enterprise NLP tasks with multilingual and reasoning capabilities.7.0#330 |
3.4#249 |
6.7#176 |
0.5#223 |
0.3#273 |
0.0#249 |
0.1#221 |
0.0#118 |
0.2#255 |
20.53s#330 |
0.1#279 |
0.7#111 |
0.1#176 |
0.0#209 |
0.0#242 |
0.1#238 |
419.3#2 |
Capabilities
Input1/5
β
Β·
Β·
Β·
Β·
Output1/5
β
Β·
Β·
Β·
Β·
Capabilities2/13
Β·
Β·
β
β
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Β·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Replicate | $0.030 | $0.250 |
IBM watsonx | $0.200 | $0.200 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Granite 4.0 Micro H | 131K | $0.017 | $0.110 | Available | |
| Granite 4 Small | β | 20K | $0.060 | $0.250 | Available |
| Granite 4.0 1B | β | β | β | β | Available |
| Granite 4.0 350M | β | β | β | β | Available |
| Granite 4.0 H Small | β | β | β | β | Available |
| Granite 4.0 H Tiny | β | β | β | β | Available |
| Granite 4.0 Micro | β | β | β | β | Available |
| Granite 3.3 8B | β | 8K | $0.030 | $0.200 | Current |
| Granite Guardian 3.3 8B | β | 8K | $0.200 | $0.200 | Available |
| Granite 3.2 2B Instruct | β | β | β | β | Available |
| Granite 3.2 8B Instruct | β | β | β | β | Available |