OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Falcon (40B) This page |
Falcon (40B) is priced at input $0.84 / 1M, output $0.84 / 1M.
Yes, Falcon (40B) can stream responses as they are generated.
Yes, Falcon (40B) supports both function calling and structured outputs.
Falcon (40B) was built by TII.