docs: fix provider model capabilities (#19729)
- mark tool streaming as supported for DeepInfra Llama 3.3 70B Instruct, based on the [DeepInfra tool calling documentation](https://docs.deepinfra.com/chat/tool-calling) - mark tool streaming as unsupported for Fireworks Llama 3.3 70B Instruct, based on the [Fireworks model page](https://fireworks.ai/models/fireworks/llama-v3p3-70b-instruct) - mark object generation as supported for Fireworks Qwen2-VL 72B Instruct, based on the [Fireworks structured outputs documentation](https://docs.fireworks.ai/structured-responses/structured-response-formatting)
N
Nick Oates committed
e1a9e5093d302e90606a68a87352076453a1a735
Parent: 0e7994c
Committed by GitHub <noreply@github.com>
on 8/26/2026, 6:13:40 PM