Phi-3.5-vision instruct (128k)
by GitHub Models · family phi · listed Aug 2024RTVW
Multimodal reasoning model for visual analysis, planning, and tool use
Current rates USD per 1M tokens
Inputfree
Outputfree
Cache read—
Cache write—
Against the market
Input price vs. maker flagships ($/1M tokens)Output price vs. maker flagships ($/1M tokens)On the record
- Model id
microsoft/phi-3.5-vision-instruct- Context window
- 128K tokens
- Max output
- 4K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Oct 2023
- Released
- 2024-08-20
- Last updated
- 2024-08-20
← All GitHub Models listings