feat(deepinfra/Qwen/Qwen3.8-2.4T-A95B): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for deepinfra/Qwen/Qwen3.8-2.4T-A95B.

---

Note

Low Risk
Metadata-only addition of a new model config file with no runtime or security logic changes.

Overview
Adds a new DeepInfra provider entry for Qwen/Qwen3.8-2.4T-A95B via providers/deepinfra/Qwen/Qwen3.8-2.4T-A95B.yaml.

The config sets per-token pricing (including cache-read input cost), prompt_caching, a 262k context and max output window, thinking: true, and mode: unknown—unlike most existing Qwen DeepInfra YAMLs, which typically use mode: chat, status, sources, and richer modality metadata.

^{Reviewed by Cursor Bugbot for commit b319fa6. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit b319fa6. Configure here.}

[cursor]

Chat model classified as unknown

Medium Severity

Qwen/Qwen3.8-2.4T-A95B is a chat/reasoning LLM, but mode is set to unknown. Consumers that route by mode will not treat this as a chat model, so the new entry cannot be used on the chat completions path. Peer DeepInfra Qwen models such as Qwen/Qwen3.8-Max use mode: chat.

 

^{Reviewed by Cursor Bugbot for commit b319fa6. Configure here.}