feat(providers): add DeepInfra provider plugin (#73038)

* feat(providers): add DeepInfra provider plugin

* feat(deepinfra): add media provider surfaces

* fix(deepinfra): satisfy provider boundary checks

* docs: add gitcrawl maintainer skill

* test: include deepinfra in live media sweeps

* fix: remove stale tts contract import

docs/providers/deepinfra.md

@@ -0,0 +1,83 @@
+---
+summary: "Use DeepInfra's unified API to access the most popular open source and frontier models in OpenClaw"
+read_when:
+  - You want a single API key for the top open source LLMs
+  - You want to run models via DeepInfra's API in OpenClaw
+---
+
+# DeepInfra
+
+DeepInfra provides a **unified API** that routes requests to the most popular open source and frontier models behind a single
+endpoint and API key. It is OpenAI-compatible, so most OpenAI SDKs work by switching the base URL.
+
+## Getting an API key
+
+1. Go to [https://deepinfra.com/](https://deepinfra.com/)
+2. Sign in or create an account
+3. Navigate to Dashboard / Keys and generate a new API key or use the auto created one
+
+## CLI setup
+
+```bash
+openclaw onboard --deepinfra-api-key <key>
+```
+
+Or set the environment variable:
+
+```bash
+export DEEPINFRA_API_KEY="<your-deepinfra-api-key>" # pragma: allowlist secret
+```
+
+## Config snippet
+
+```json5
+{
+  env: { DEEPINFRA_API_KEY: "<your-deepinfra-api-key>" }, // pragma: allowlist secret
+  agents: {
+    defaults: {
+      model: { primary: "deepinfra/deepseek-ai/DeepSeek-V3.2" },
+    },
+  },
+}
+```
+
+## Supported OpenClaw surfaces
+
+The bundled plugin registers all DeepInfra surfaces that match current
+OpenClaw provider contracts:
+
+| Surface                  | Default model                      | OpenClaw config/tool                                     |
+| ------------------------ | ---------------------------------- | -------------------------------------------------------- |
+| Chat / model provider    | `deepseek-ai/DeepSeek-V3.2`        | `agents.defaults.model`                                  |
+| Image generation/editing | `black-forest-labs/FLUX-1-schnell` | `image_generate`, `agents.defaults.imageGenerationModel` |
+| Media understanding      | `moonshotai/Kimi-K2.5` for images  | inbound image understanding                              |
+| Speech-to-text           | `openai/whisper-large-v3-turbo`    | inbound audio transcription                              |
+| Text-to-speech           | `hexgrad/Kokoro-82M`               | `messages.tts.provider: "deepinfra"`                     |
+| Video generation         | `Pixverse/Pixverse-T2V`            | `video_generate`, `agents.defaults.videoGenerationModel` |
+| Memory embeddings        | `BAAI/bge-m3`                      | `agents.defaults.memorySearch.provider: "deepinfra"`     |
+
+DeepInfra also exposes reranking, classification, object-detection, and other
+native model types. OpenClaw does not currently have first-class provider
+contracts for those categories, so this plugin does not register them yet.
+
+## Available models
+
+OpenClaw dynamically discovers available DeepInfra models at startup. Use
+`/models deepinfra` to see the full list of models available.
+
+Any model available on [DeepInfra.com](https://deepinfra.com/) can be used with the `deepinfra/` prefix:
+
+```
+deepinfra/MiniMaxAI/MiniMax-M2.5
+deepinfra/deepseek-ai/DeepSeek-V3.2
+deepinfra/moonshotai/Kimi-K2.5
+deepinfra/zai-org/GLM-5.1
+...and many more
+```
+
+## Notes
+
+- Model refs are `deepinfra/<provider>/<model>` (e.g., `deepinfra/Qwen/Qwen3-Max`).
+- Default model: `deepinfra/deepseek-ai/DeepSeek-V3.2`
+- Base URL: `https://api.deepinfra.com/v1/openai`
+- Native video generation uses `https://api.deepinfra.com/v1/inference/<model>`.

docs/providers/models.md

@@ -31,6 +31,7 @@ model as `provider/model`.
 - [Chutes](/providers/chutes)
 - [ComfyUI](/providers/comfy)
 - [Cloudflare AI Gateway](/providers/cloudflare-ai-gateway)
+- [DeepInfra](/providers/deepinfra)
 - [fal](/providers/fal)
 - [Fireworks](/providers/fireworks)
 - [GLM models](/providers/glm)