feat(deepinfra/Qwen/Qwen3.8-27B): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for deepinfra/Qwen/Qwen3.8-27B.

---

Note

Low Risk
Metadata-only addition with no runtime or application logic changes; incorrect fields (e.g. mode: unknown, missing status) could affect how the model is exposed or routed until aligned with other DeepInfra entries.

Overview
Adds a new DeepInfra provider entry for Qwen/Qwen3.8-27B via providers/deepinfra/Qwen/Qwen3.8-27B.yaml.

The config registers token pricing (including prompt-caching read cost), a 262k context/max_tokens window, thinking: true, and image as an input modality. mode is set to unknown, and unlike most sibling Qwen DeepInfra YAMLs it omits fields such as status, sources, supportedModes, provisioning, and text output modalities.

^{Reviewed by Cursor Bugbot for commit b6302b0. 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 3 potential issues.

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

^{Reviewed by Cursor Bugbot for commit b6302b0. Configure here.}

[cursor]

Wrong primary mode set

High Severity

mode is set to unknown for Qwen/Qwen3.8-27B, a chat vision-language model. Sibling DeepInfra Qwen chat models such as Qwen3.5-27B, Qwen3.6-27B, and Qwen3.8-Max use mode: chat. Consumers that route or filter by chat mode will not treat this model as a chat endpoint.

 

^{Reviewed by Cursor Bugbot for commit b6302b0. Configure here.}

[cursor]

Incomplete input and output modalities

High Severity

modalities lists only image input and omits output entirely. Qwen3.8-27B is a vision-language chat model that accepts text (and typically video) and returns text. Sibling configs such as Qwen3.5-27B and Qwen3.8-Max declare text input and text output. Clients relying on this metadata will wrongly assume text is unsupported.

 

^{Reviewed by Cursor Bugbot for commit b6302b0. Configure here.}

[cursor]

Missing tool and JSON features

Medium Severity

features only includes prompt_caching. Comparable DeepInfra Qwen chat models (Qwen3.5-27B, Qwen3.8-Max, Qwen3.7-Max) also declare function_calling and json_output, and external docs confirm tool use for Qwen3.8-27B. Capability discovery based on this file will under-report supported features.

 

^{Reviewed by Cursor Bugbot for commit b6302b0. Configure here.}