Granite 3 3 8B Instruct
Granite 3 3 8B Instruct is a text model from
IBM watsonx with a context window of 8K tokens and max output of 8K tokens. Pricing starts at 0.20 per million input tokens and 0.20 per million output tokens (cheapest at Replicate).
Capabilities
✗ Vision✓ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output
Specifications
| Model Key | watsonx/ibm/granite-3-3-8b-instruct |
| Provider | |
| Provider ID | watsonx |
| Mode | Text |
| Canonical Name | granite-3.3-8b |
| Context Window | 8K tokens |
| Max Output | 8K tokens |
Pricing
| Type | Per 1K Tokens | Per 1M Tokens |
|---|---|---|
| Input Tokens | 0.000200 | 0.200 |
| Output Tokens | 0.000200 | 0.200 |
Price Comparison by Provider
Compare prices for Granite 3 3 8B Instruct across different providers. The same model may be available through multiple providers at different price points.
Provider | Model Key | Input Price, $ | Output Price, $ |
|---|---|---|---|
| watsonx/ibm/granite-3-3-8b-instruct | 0.200 | 0.200 | |
| replicate/ibm-granite/granite-3.3-8b-instruct | 0.030 | 0.250 |
All Variants
All available versions, regions, and API endpoints for Granite 3 3 8B Instruct.
Model Key | Provider | Mode | Input Price, $ | Output Price, $ | Context | Max Output | Vision | Functions |
|---|---|---|---|---|---|---|---|---|
| watsonx/ibm/granite-3-3-8b-instruct | Text | 0.200 | 0.200 | 8K | 8K | no | yes | |
| watsonx/ibm/granite-3-8b-instruct | Text | 0.200 | 0.200 | 8K | 1K | no | yes | |
| replicate/ibm-granite/granite-3.3-8b-instruct | Text | 0.030 | 0.250 | N/A | N/A | no | yes |