# Infery.ai

## Docs

- [Text-to-speech](https://docs.infery.ai/api-reference/audio/speech.md): POST /v1/audio/speech — synthesise speech from text.
- [Speech-to-text](https://docs.infery.ai/api-reference/audio/transcriptions.md): POST /v1/audio/transcriptions — transcribe audio to text.
- [Authentication](https://docs.infery.ai/api-reference/authentication.md): Bearer API keys, per-key quotas, and key lifecycle.
- [Chat completions](https://docs.infery.ai/api-reference/chat-completions.md): POST /v1/chat/completions — OpenAI-compatible text and multimodal chat.
- [Embeddings](https://docs.infery.ai/api-reference/embeddings.md): POST /v1/embeddings — dense vector embeddings for text.
- [Errors](https://docs.infery.ai/api-reference/errors.md): OpenAI-compatible error envelope with Infery-specific codes.
- [Download file contents](https://docs.infery.ai/api-reference/files/content.md): GET /v1/files/{fileId}/content — stream the raw file bytes.
- [Delete a file](https://docs.infery.ai/api-reference/files/delete.md): DELETE /v1/files/{fileId} — soft-delete in DB, hard-delete in GCS.
- [List files](https://docs.infery.ai/api-reference/files/list.md): GET /v1/files — list uploaded files in the current workspace.
- [Retrieve file metadata](https://docs.infery.ai/api-reference/files/retrieve.md): GET /v1/files/{fileId} — fetch metadata for a single file.
- [Upload a file](https://docs.infery.ai/api-reference/files/upload.md): POST /v1/files — upload a file and get back a reusable file_id.
- [Edit an image](https://docs.infery.ai/api-reference/images/edits.md): POST /v1/images/edits — modify an existing image with a prompt.
- [Generate an image](https://docs.infery.ai/api-reference/images/generations.md): POST /v1/images/generations — text-to-image generation.
- [API overview](https://docs.infery.ai/api-reference/introduction.md): OpenAI-compatible REST API for text, images, voice, video, music and embeddings.
- [Models](https://docs.infery.ai/api-reference/models.md): GET /v1/models — list available model slugs and capabilities.
- [Music](https://docs.infery.ai/api-reference/music.md): Generate full songs from a prompt.
- [Rate limits](https://docs.infery.ai/api-reference/rate-limits.md): Per-key and global rate limits with back-off guidance.
- [Create video generation](https://docs.infery.ai/api-reference/videos/generations.md): POST /v1/videos/generations — submit an async video generation job.
- [Get video generation status](https://docs.infery.ai/api-reference/videos/status.md): GET /v1/videos/generations/{jobId} — poll for job status and result.
- [Credits](https://docs.infery.ai/billing/credits.md): One balance, every modality, predictable costs.
- [Subscription plans](https://docs.infery.ai/billing/subscription-plans.md): Monthly credit allowance, team size, limits and feature flags per plan.
- [Topups](https://docs.infery.ai/billing/topups.md): One-off credit purchases that never expire.
- [Usage & invoices](https://docs.infery.ai/billing/usage.md): See exactly what you spent, on what model, by which API key — and export it.
- [Core concepts](https://docs.infery.ai/concepts.md): Workspaces, plans, credits, Playground and API — a mental model for the platform.
- [Audio: TTS and STT](https://docs.infery.ai/guides/audio-tts-stt.md): Generate speech, transcribe recordings, handle long-form audio and streaming.
- [Embeddings & RAG](https://docs.infery.ai/guides/embeddings-and-rag.md): From a folder of documents to a working retrieval-augmented chat — end to end.
- [Setting up fallbacks](https://docs.infery.ai/guides/fallback-setup.md): Survive provider outages and rate limits without changing client code.
- [File attachments in chat](https://docs.infery.ai/guides/file-attachments-in-chat.md): PDFs, images, audio, video — inline or by file_id.
- [Image generation](https://docs.infery.ai/guides/image-generation.md): Choose the right model, write better prompts, and persist what you generate.
- [Music generation](https://docs.infery.ai/guides/music-generation.md): Pick a model, write prompts that render, handle async jobs, and control Suno custom mode.
- [Migrating from OpenAI](https://docs.infery.ai/guides/openai-sdk-migration.md): Point your existing code at Infery in two lines. No SDK swap.
- [Rate limits & retries](https://docs.infery.ai/guides/rate-limits-and-retries.md): Survive 429s with backoff, queueing, and fallbacks — without hammering the gateway.
- [Streaming](https://docs.infery.ai/guides/streaming.md): Server-Sent Events the OpenAI way, plus the Infery cost chunk.
- [Tool calling](https://docs.infery.ai/guides/tool-calling.md): Let the model invoke functions, look up data, and act on the world.
- [Video generation](https://docs.infery.ai/guides/video-generation.md): Async submission, polling, image-to-video, and persistence.
- [Introduction](https://docs.infery.ai/introduction.md): Infery.ai is an AI workspace for text, images, voice and video — with an OpenAI-compatible API.
- [Alibaba (Qwen)](https://docs.infery.ai/models/alibaba.md): Qwen text, vision, image, audio, video, embedding and rerank models.
- [Anthropic](https://docs.infery.ai/models/anthropic.md): Claude Opus, Sonnet and Haiku model families.
- [Capabilities](https://docs.infery.ai/models/capabilities.md): What each chat model can do — chat, streaming, vision, PDF, tools, JSON mode.
- [Model catalog](https://docs.infery.ai/models/catalog.md): The full list of models live on Infery — browse by provider or modality.
- [Choosing a model](https://docs.infery.ai/models/choosing.md): A pragmatic guide to picking between the major chat models.
- [DeepSeek](https://docs.infery.ai/models/deepseek.md): DeepSeek V3.2 chat and reasoning models.
- [Google](https://docs.infery.ai/models/google.md): Gemini, Imagen, Veo, Lyria — text, images, video, audio and music.
- [OpenAI](https://docs.infery.ai/models/openai.md): GPT, o-series, DALL-E, Sora, Whisper, TTS and embeddings.
- [Suno](https://docs.infery.ai/models/suno.md): AI music generation — full songs, vocals, instrumentals and sound effects.
- [xAI](https://docs.infery.ai/models/xai.md): Grok text, image, audio and video models.
- [Bookmarks](https://docs.infery.ai/playground/bookmarks.md): Pin important messages and revisit them across chats and projects.
- [Chats and projects](https://docs.infery.ai/playground/chats-and-projects.md): How conversations are organised in the Playground.
- [Files and attachments](https://docs.infery.ai/playground/files-and-attachments.md): Drop files into a chat. Reuse generated images across messages. Download and share.
- [Modalities](https://docs.infery.ai/playground/modalities.md): Chat, Image, TTS, STT, Video and Music — one Playground, six creative workflows.
- [Playground overview](https://docs.infery.ai/playground/overview.md): A full UI for chatting with models, generating content and organising work into projects.
- [Sharing chats and projects](https://docs.infery.ai/playground/sharing.md): Granular access control for Playground content — private, workspace-wide, or specific users.
- [Quickstart](https://docs.infery.ai/quickstart.md): Five minutes from sign-up to your first chat response and first API call.
- [Changelog](https://docs.infery.ai/reference/changelog.md): What shipped, when, and what's next.
- [Security](https://docs.infery.ai/reference/security.md): How we protect your data, your keys, and your inferences.
- [Budget alerts](https://docs.infery.ai/workspaces/budget-alerts.md): Know before you run out. Automatic notifications at spend thresholds.
- [Fallback chains](https://docs.infery.ai/workspaces/fallback-chains.md): Route automatically to a backup model when the primary fails or rate-limits.
- [Members and roles](https://docs.infery.ai/workspaces/members-and-roles.md): Invite teammates, assign roles, and keep each person on a need-to-know basis.
- [Notifications](https://docs.infery.ai/workspaces/notifications.md): Subscribe members to the events that matter over Slack, email and webhooks.
- [Quotas and presets](https://docs.infery.ai/workspaces/quotas-and-presets.md): Cap spend and traffic per user, per API key — with reusable presets.

## OpenAPI Specs

- [openapi](https://docs.infery.ai/openapi.json)