# Pika API

> Pika API provides callable model operations for image, video, audio, music, speech, transcription, dubbing, upscaling, and language models through one API key. Use this file to discover an operation, then read its linked specification before making a request.

The catalog and per-operation specifications are the runtime source of truth. Do not infer endpoint paths, request fields, enum values, pricing, or model support from a model name or from prior knowledge.

## Start Here

- [Create an account or sign in](https://dev.pika.art/login): Create a Pika API account, manage membership, and access the dashboard.
- [Dashboard](https://dev.pika.art/dashboard): Create and manage API keys, usage, and billing.
- [API keys](https://dev.pika.art/keys): Create, rotate, and revoke keys.
- [Agent onboarding](https://dev.pika.art/agent): Copy the short Pika onboarding prompt into a coding agent, app builder, or chat assistant.
- [Models](https://dev.pika.art/models): Browse the human-readable model catalog and playgrounds.
- [Pricing](https://dev.pika.art/pricing): Review current model pricing before running paid generations.

## Environments

- Documentation and model pages: `https://dev.pika.art`
- Customer API base URL: `https://api.dev.pika.art`
- Recommended local secret name: `PIKA_API_KEY`
- Authentication header: `X-API-Key: $PIKA_API_KEY` or `Authorization: Bearer $PIKA_API_KEY`. Google's `x-goog-api-key` is not accepted.

Never place an API key in browser code, a URL, source control, generated output, screenshots, or chat. Store it in the runtime's server-side secret manager or local environment. A browser application must call Pika through its own authenticated server route.

## Documentation Precedence

Use these sources in this order:

1. For current availability, request fields, required inputs, enum values, and pricing metadata, use `GET https://api.dev.pika.art/catalog/apis/{api_id}?expand=inputs`. Send the slashes in `api_id` literally (`bytedance/seedance-2.0/text-to-video`).
2. For the exact submit endpoint, request and response examples, polling behavior, uploads, and errors, use the operation's linked `https://dev.pika.art/llms/...` specification.
3. Use this `llms.txt` file for discovery and routing, not as a substitute for the selected operation's specification.

If a prose example conflicts with the catalog `input_schema`, follow the catalog schema. If an operation is missing from the public catalog or is not active, do not call it.

## Public Catalog

The catalog does not require an API key and can be used to verify connectivity without creating a paid generation.

- List operations: `GET https://api.dev.pika.art/catalog/apis`
- Inspect one operation: `GET https://api.dev.pika.art/catalog/apis/{api_id}?expand=inputs`

The detail response includes the current `api_id`, category, display name, pricing metadata, concrete HTTP method and path, and expanded JSON `input_schema`.

## Account Balance

Read the org's balance before a paid submit. These endpoints take the same API key as a generation and are never charged.

- Balance: `GET https://api.dev.pika.art/billing/balance`
- Spend history: `GET https://api.dev.pika.art/billing/spend/daily?start_date=YYYY-MM-DD&end_date=YYYY-MM-DD`, grouped by API key and model. Both dates are required and inclusive, the range cannot exceed 366 days, and `api_key_id` and `model` narrow the result. Amounts use the same micro-USD unit as the balance.

### The balance object

- `org_id` (string): The org the key belongs to.
- `balance_micro_usd` (integer): Prepaid balance in micro-USD. Divide by 1,000,000 to compare it against the US dollar prices in the catalog and in an operation's specification.
- `postpaid` (object): Present only when the org bills by invoice, carrying `effective_at` and `active`. Once `active` is true the prepaid balance is not the spend gate — the invoice cycle limit is, and exceeding it fails a submit with `cycle_limit_exceeded`, not `insufficient_balance`. `null` means a plain prepaid org and nothing else.

Estimate the cost of the intended request from the operation's pricing, then read the balance and confirm it covers that cost. If it does not, report the shortfall in dollars and stop; do not submit a request to discover whether it can be paid for. A `200` here also proves the key is active, which is what separates an inactive key from an empty balance after a `403`.

## Agent Workflow

1. Determine the user's intended output and available inputs: text, image, video, audio, or a combination.
2. Shortlist operations from the model list below. Recommend one best fit and, only when useful, one alternative. Explain the tradeoff in quality, speed, capability, or cost.
3. Fetch the selected operation's linked specification and its live catalog record before writing request code.
4. Check that `PIKA_API_KEY` is configured without printing or exposing it. If absent, guide the user to [sign in](https://dev.pika.art/login) and create a key in the dashboard.
5. Read the balance and confirm it covers the requests you are about to make. If it does not, report the shortfall and stop there.
6. State the selected model, operation, important settings, and number of paid requests before submitting. A user's approval of one generation does not authorize a batch or additional variants.
7. Execute the request, wait for a terminal result, save or integrate the output, and report the model used and the next recommended capability.

## Media API

All non-LLM generation operations use concrete asynchronous REST endpoints.

- Submit: `POST https://api.dev.pika.art/v1/media/{vendor}/{model}/{function}` using the exact path and JSON body from the selected operation's specification.
- The submit response returns a job object containing `id` and `status`. Preserve the returned `id` as the request ID.
- Poll: `GET https://api.dev.pika.art/v1/media/jobs/{request_id}` until `status` is `completed` or `failed`.
- Result: after completion, `GET https://api.dev.pika.art/v1/media/jobs/{request_id}/content` returns `{ "url": "..." }`.
- Do not request content before the job is complete.

For retry-safe submits, send a stable `Idempotency-Key` for the same request body. Never reuse an idempotency key with a different body. A failed job replays on its key, so retry a failure with a fresh key.

## Reference Uploads

When an operation needs a local image, video, or audio file:

1. Send `POST https://api.dev.pika.art/v1/media/uploads` with `X-API-Key` and JSON `{ "content_type": "image/png", "size_bytes": 12345 }` using the file's real MIME type and exact byte length.
2. The response returns a temporary `upload_url`, the `headers` to send with it, and a hosted `url`.
3. Immediately `PUT` the raw file bytes to `upload_url`, sending the returned `headers` verbatim — both `Content-Type` and `Content-Length` are signed, and storage returns a bare 403 if either is missing or differs.
4. Pass the hosted `url`, not the temporary upload URL or local path, into the model request field named by the selected operation's schema.

The presigned URL is valid for 5 minutes. An unsupported `content_type` returns `415`; over the size cap (20 MB image and audio, 50 MB video) returns `413`. A public URL you already host needs no upload — pass it straight into the input field.

## Language Model API

Language-model operations are synchronous. Fetch the selected model's specification before choosing a protocol.

- OpenAI-compatible: `POST https://api.dev.pika.art/v1/chat/completions`
- Anthropic Messages: `POST https://api.dev.pika.art/anthropic/v1/messages`
- Google GenAI: `POST https://api.dev.pika.art/genai/v1beta/models/{model}:generateContent`

Streaming is supported: send `"stream": true` on the OpenAI and Anthropic surfaces, and call `:streamGenerateContent` instead of `:generateContent` on GenAI.

Use only the protocol and model identifier from the selected model's specification.

## Errors and Retries

- `401`: API key missing or invalid. Stop and correct authentication.
- `403`: key inactive or balance insufficient, returned as the failed job envelope on a media submit. Branch on `error.code`, or read `GET https://api.dev.pika.art/billing/balance` to tell the two apart — a `200` means the key is active and the request was priced above the balance. Report the shortfall and direct the user to top up in the dashboard. Do not retry the same submit.
- `404`: operation, job, or file not found. Recheck the current catalog and request ID.
- `409`: result requested too early or an idempotency key was reused with a different body.
- `413` / `415`: upload too large, or an unsupported `content_type` on `/v1/media/uploads`.
- `422`: request validation or unpriceable parameter combination. Correct the request from the live schema; do not retry unchanged.
- `429`: rate or concurrency limit reached, returned as the failed job envelope on a media submit. Respect `Retry-After` and retry with bounded backoff.
- `502` / `504`: upstream provider failed or timed out; synchronous surfaces only.
- `503`: Pika-side dependency unavailable (auth, billing, or dispatch). Retry with bounded backoff; surface the failure if it persists.

Every error body is JSON. Request-level errors (auth, unknown path, schema validation, idempotency conflict) are `{"message": "..."}`.

Never silently switch models after a paid request fails. Explain the failure and obtain approval before submitting to a different model.

## Completion Standard

A successful integration ends with working code or a generated artifact, the selected model and operation recorded, the output URL saved or integrated, secrets kept server-side, and a clear next step. Do not stop after merely describing the API.

## Policies and Support

- [Terms of Service](https://dev.pika.art/terms-of-service)
- [Privacy Policy](https://dev.pika.art/privacy-policy)
- [Acceptable Use Policy](https://pika.art/acceptable-use-policy)
- [Email API support](mailto:api@pika.art)

## Recommended models

Popular starting points per task; the full catalog is below. Recommend one, not the list.

- Text to Video: [Seedance 2.0](https://dev.pika.art/llms/bytedance/seedance-2.0/text-to-video), [MiniMax H3](https://dev.pika.art/llms/minimax/h3/text-to-video), [Pika 2.5](https://dev.pika.art/llms/pika/pika-2.5/text-to-video)
- Image to Video: [Seedance 2.0](https://dev.pika.art/llms/bytedance/seedance-2.0/image-to-video), [MiniMax H3](https://dev.pika.art/llms/minimax/h3/image-to-video), [Pika 2.5](https://dev.pika.art/llms/pika/pika-2.5/image-to-video)
- Text to Image: [Seedream 5.0 Pro Text to Image](https://dev.pika.art/llms/bytedance/seedream-5.0-pro/text-to-image), [Nano Banana 2](https://dev.pika.art/llms/google/gemini-3.1-flash-image/text-to-image), [GPT Image 2](https://dev.pika.art/llms/openai/gpt-image-2/text-to-image)
- Image Editing: [Seedream 5.0 Pro Image Editing](https://dev.pika.art/llms/bytedance/seedream-5.0-pro/image-to-image), [Nano Banana 2](https://dev.pika.art/llms/google/gemini-3.1-flash-image/image-to-image), [GPT Image 2](https://dev.pika.art/llms/openai/gpt-image-2/image-to-image)
- Text to Speech: [Eleven Multilingual v2](https://dev.pika.art/llms/elevenlabs/eleven-multilingual-v2/text-to-speech), [MiniMax Speech 2.8 HD](https://dev.pika.art/llms/minimax/minimax-speech-2.8-hd/text-to-speech)
- Music: [MiniMax Music 3.0](https://dev.pika.art/llms/minimax/minimax-music-3.0/text-to-audio), [Sonilo v1.1 Music](https://dev.pika.art/llms/sonilo/sonilo-v1.1-music/text-to-music)
- Transcription: [Eleven Scribe](https://dev.pika.art/llms/elevenlabs/eleven-scribe/transcription), [Whisper](https://dev.pika.art/llms/openai/whisper/transcription)
- LLM: [Claude Fable 5](https://dev.pika.art/llms/anthropic/claude-fable-5), [GPT-5.6 Sol](https://dev.pika.art/llms/openai/gpt-5.6-sol), [Gemini 3.1 Pro](https://dev.pika.art/llms/google/gemini-3.1-pro)

## Models

118 callable operations. A model can appear more than once when it supports multiple functions. Fetch the linked specification for the operation you intend to call.

### Pika

- [Pika 2.5](https://dev.pika.art/models/pika/pika-2.5/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/pika/pika-2.5/image-to-video
- [Pika 2.5](https://dev.pika.art/models/pika/pika-2.5/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/pika/pika-2.5/text-to-video
- [Pikadditions](https://dev.pika.art/models/pika/pikadditions/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/pika/pikadditions/video-to-video
- [Pikaswaps](https://dev.pika.art/models/pika/pikaswaps/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/pika/pikaswaps/video-to-video
- [Pikaffects](https://dev.pika.art/models/pika/pikaffects/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/pika/pikaffects/image-to-video
- [Pikaffects](https://dev.pika.art/models/pika/pikaffects/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/pika/pikaffects/video-to-video
- [Pika 2.5 Keyframe](https://dev.pika.art/models/pika/pikaframes/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/pika/pikaframes/image-to-video

### Alibaba

- [Happyhorse 1.1 Image To Video](https://dev.pika.art/models/alibaba/happyhorse-1.1/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.1/image-to-video
- [Happyhorse 1.1 Reference To Video](https://dev.pika.art/models/alibaba/happyhorse-1.1/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.1/reference-to-video
- [Happyhorse 1.1 Text To Video](https://dev.pika.art/models/alibaba/happyhorse-1.1/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.1/text-to-video
- [Happyhorse 1.0](https://dev.pika.art/models/alibaba/happyhorse-1.0/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.0/image-to-video
- [Happyhorse 1.0](https://dev.pika.art/models/alibaba/happyhorse-1.0/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.0/reference-to-video
- [Happyhorse 1.0](https://dev.pika.art/models/alibaba/happyhorse-1.0/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.0/text-to-video
- [Happyhorse 1.0](https://dev.pika.art/models/alibaba/happyhorse-1.0/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/alibaba/happyhorse-1.0/video-to-video

### Anthropic

- [Claude Fable 5](https://dev.pika.art/models/anthropic/claude-fable-5) (LLM, sync). Spec: https://dev.pika.art/llms/anthropic/claude-fable-5
- [Claude Sonnet 5](https://dev.pika.art/models/anthropic/claude-sonnet-5) (LLM, sync). Spec: https://dev.pika.art/llms/anthropic/claude-sonnet-5
- [Claude Opus 5](https://dev.pika.art/models/anthropic/claude-opus-5) (LLM, sync). Spec: https://dev.pika.art/llms/anthropic/claude-opus-5
- [Anthropic Claude Haiku 4.5](https://dev.pika.art/models/anthropic/claude-haiku-4.5) (LLM, sync). Spec: https://dev.pika.art/llms/anthropic/claude-haiku-4.5

### Black Forest Labs

- [FLUX 3](https://dev.pika.art/models/black-forest-labs/flux-3-video/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/black-forest-labs/flux-3-video/image-to-video
- [FLUX 3](https://dev.pika.art/models/black-forest-labs/flux-3-video/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/black-forest-labs/flux-3-video/text-to-video
- [FLUX 3 Video Extension](https://dev.pika.art/models/black-forest-labs/flux-3-video/video-to-video) (Video Extension, async). Spec: https://dev.pika.art/llms/black-forest-labs/flux-3-video/video-to-video

### ByteDance

- [Seedance 2.5](https://dev.pika.art/models/bytedance/seedance-2.5/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.5/image-to-video
- [Seedance 2.5](https://dev.pika.art/models/bytedance/seedance-2.5/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.5/reference-to-video
- [Seedance 2.5](https://dev.pika.art/models/bytedance/seedance-2.5/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.5/text-to-video
- [Seedance 2.0](https://dev.pika.art/models/bytedance/seedance-2.0/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0/image-to-video
- [Seedance 2.0](https://dev.pika.art/models/bytedance/seedance-2.0/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0/reference-to-video
- [Seedance 2.0](https://dev.pika.art/models/bytedance/seedance-2.0/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0/text-to-video
- [Seedance 2.0 Fast](https://dev.pika.art/models/bytedance/seedance-2.0-fast/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-fast/image-to-video
- [Seedance 2.0 Fast](https://dev.pika.art/models/bytedance/seedance-2.0-fast/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-fast/reference-to-video
- [Seedance 2.0 Fast](https://dev.pika.art/models/bytedance/seedance-2.0-fast/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-fast/text-to-video
- [Seedance 2.0 Mini](https://dev.pika.art/models/bytedance/seedance-2.0-mini/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-mini/image-to-video
- [Seedance 2.0 Mini](https://dev.pika.art/models/bytedance/seedance-2.0-mini/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-mini/reference-to-video
- [Seedance 2.0 Mini](https://dev.pika.art/models/bytedance/seedance-2.0-mini/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/bytedance/seedance-2.0-mini/text-to-video
- [Seedream 5.0 Pro Image Editing](https://dev.pika.art/models/bytedance/seedream-5.0-pro/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-5.0-pro/image-to-image
- [Seedream 5.0 Pro Text to Image](https://dev.pika.art/models/bytedance/seedream-5.0-pro/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-5.0-pro/text-to-image
- [Seedream 5.0 Lite Image Editing](https://dev.pika.art/models/bytedance/seedream-5.0-lite/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-5.0-lite/image-to-image
- [Seedream 5.0 Lite](https://dev.pika.art/models/bytedance/seedream-5.0-lite/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-5.0-lite/text-to-image
- [Seedream 4.5](https://dev.pika.art/models/bytedance/seedream-4.5/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-4.5/text-to-image
- [Seedream 4.0 Image Editing](https://dev.pika.art/models/bytedance/seedream-4.0/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-4.0/image-to-image
- [Seedream 4.0](https://dev.pika.art/models/bytedance/seedream-4.0/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/bytedance/seedream-4.0/text-to-image
- [Seed Audio 1.0](https://dev.pika.art/models/bytedance/seed-audio-1.0/text-to-audio) (Text to Audio, async). Spec: https://dev.pika.art/llms/bytedance/seed-audio-1.0/text-to-audio

### DeepSeek

- [DeepSeek V4 Pro](https://dev.pika.art/models/deepseek/deepseek-v4-pro) (LLM, sync). Spec: https://dev.pika.art/llms/deepseek/deepseek-v4-pro
- [DeepSeek V4 Flash](https://dev.pika.art/models/deepseek/deepseek-v4-flash-0731) (LLM, sync). Spec: https://dev.pika.art/llms/deepseek/deepseek-v4-flash-0731
- [DeepSeek V4 Flash](https://dev.pika.art/models/deepseek/deepseek-v4-flash) (LLM, sync). Spec: https://dev.pika.art/llms/deepseek/deepseek-v4-flash

### ElevenLabs

- [Eleven Multilingual v2](https://dev.pika.art/models/elevenlabs/eleven-multilingual-v2/text-to-speech) (Text to Speech, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-multilingual-v2/text-to-speech
- [Eleven Multilingual STS v2](https://dev.pika.art/models/elevenlabs/eleven-multilingual-sts-v2/speech-to-speech) (Speech to Speech, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-multilingual-sts-v2/speech-to-speech
- [Eleven Scribe](https://dev.pika.art/models/elevenlabs/eleven-scribe/transcription) (Transcription, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-scribe/transcription
- [Eleven Text to Dialogue](https://dev.pika.art/models/elevenlabs/eleven-text-to-dialogue/text-to-speech) (Text to Speech, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-text-to-dialogue/text-to-speech
- [Eleven Text to Sound v2](https://dev.pika.art/models/elevenlabs/eleven-text-to-sound-v2/sound-effects) (Sound Effects, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-text-to-sound-v2/sound-effects
- [Eleven Turbo v2.5](https://dev.pika.art/models/elevenlabs/eleven-turbo-v2-5/text-to-speech) (Text to Speech, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-turbo-v2-5/text-to-speech
- [Eleven Voice Dubbing](https://dev.pika.art/models/elevenlabs/eleven-voice-dubbing/dubbing) (Dubbing, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-voice-dubbing/dubbing
- [Eleven Voice Isolation](https://dev.pika.art/models/elevenlabs/eleven-voice-isolation/voice-isolation) (Voice Isolation, async). Spec: https://dev.pika.art/llms/elevenlabs/eleven-voice-isolation/voice-isolation

### Google

- [Gemini Omni Flash](https://dev.pika.art/models/google/gemini-omni-flash/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/google/gemini-omni-flash/text-to-video
- [Gemini Omni Flash](https://dev.pika.art/models/google/gemini-omni-flash/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/google/gemini-omni-flash/image-to-video
- [Gemini Omni Flash](https://dev.pika.art/models/google/gemini-omni-flash/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/google/gemini-omni-flash/reference-to-video
- [Gemini Omni Flash](https://dev.pika.art/models/google/gemini-omni-flash/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/google/gemini-omni-flash/video-to-video
- [Veo 3.1](https://dev.pika.art/models/google/veo-3.1/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/google/veo-3.1/text-to-video
- [Veo 3.1 Video Extension](https://dev.pika.art/models/google/veo-3.1/video-extension) (Video Extension, async). Spec: https://dev.pika.art/llms/google/veo-3.1/video-extension
- [Veo 3.1 Fast](https://dev.pika.art/models/google/veo-3.1-fast/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/google/veo-3.1-fast/text-to-video
- [Veo 3.1 Fast Video Extension](https://dev.pika.art/models/google/veo-3.1-fast/video-extension) (Video Extension, async). Spec: https://dev.pika.art/llms/google/veo-3.1-fast/video-extension
- [Veo 3.1 Lite](https://dev.pika.art/models/google/veo-3.1-lite/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/google/veo-3.1-lite/image-to-video
- [Nano Banana Pro](https://dev.pika.art/models/google/gemini-3-pro-image/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3-pro-image/image-to-image
- [Nano Banana Pro](https://dev.pika.art/models/google/gemini-3-pro-image/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3-pro-image/text-to-image
- [Nano Banana 2](https://dev.pika.art/models/google/gemini-3.1-flash-image/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3.1-flash-image/image-to-image
- [Nano Banana 2](https://dev.pika.art/models/google/gemini-3.1-flash-image/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3.1-flash-image/text-to-image
- [Nano Banana 2 Lite](https://dev.pika.art/models/google/gemini-3.1-flash-lite-image/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3.1-flash-lite-image/image-to-image
- [Nano Banana 2 Lite](https://dev.pika.art/models/google/gemini-3.1-flash-lite-image/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/google/gemini-3.1-flash-lite-image/text-to-image
- [Lyria 3 Pro](https://dev.pika.art/models/google/lyria-3-pro/text-to-audio) (Text to Audio, async). Spec: https://dev.pika.art/llms/google/lyria-3-pro/text-to-audio
- [Lyria 3](https://dev.pika.art/models/google/lyria-3/text-to-audio) (Text to Audio, async). Spec: https://dev.pika.art/llms/google/lyria-3/text-to-audio
- [Lyria 2](https://dev.pika.art/models/google/lyria-2/sound-effects) (Music, async). Spec: https://dev.pika.art/llms/google/lyria-2/sound-effects
- [Gemini 3.6 Flash](https://dev.pika.art/models/google/gemini-3.6-flash) (LLM, sync). Spec: https://dev.pika.art/llms/google/gemini-3.6-flash
- [Gemini 3.5 Flash-Lite](https://dev.pika.art/models/google/gemini-3.5-flash-lite) (LLM, sync). Spec: https://dev.pika.art/llms/google/gemini-3.5-flash-lite
- [Gemini 3.1 Pro](https://dev.pika.art/models/google/gemini-3.1-pro) (LLM, sync). Spec: https://dev.pika.art/llms/google/gemini-3.1-pro

### Kling (Kuaishou)

- [Kling 3.0](https://dev.pika.art/models/kling/kling-3.0/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/kling/kling-3.0/text-to-video
- [Kling 3.0](https://dev.pika.art/models/kling/kling-3.0/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/kling/kling-3.0/image-to-video
- [Kling 3.0](https://dev.pika.art/models/kling/kling-3.0/omni-video) (Omni Video, async). Spec: https://dev.pika.art/llms/kling/kling-3.0/omni-video
- [Kling 3.0](https://dev.pika.art/models/kling/kling-3.0/motion-control) (Motion Control, async). Spec: https://dev.pika.art/llms/kling/kling-3.0/motion-control
- [Kling 3.0 Turbo](https://dev.pika.art/models/kling/kling-3.0-turbo/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/kling/kling-3.0-turbo/text-to-video
- [Kling 3.0 Turbo](https://dev.pika.art/models/kling/kling-3.0-turbo/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/kling/kling-3.0-turbo/image-to-video
- [Kling AI Avatar v2](https://dev.pika.art/models/kling/kling-ai-avatar-v2/avatar) (Avatar, async). Spec: https://dev.pika.art/llms/kling/kling-ai-avatar-v2/avatar
- [Kling Lipsync](https://dev.pika.art/models/kling/kling-lipsync/avatar) (Avatar, async). Spec: https://dev.pika.art/llms/kling/kling-lipsync/avatar
- [Kling Audio](https://dev.pika.art/models/kling/kling-audio/text-to-audio) (Text to Audio, async). Spec: https://dev.pika.art/llms/kling/kling-audio/text-to-audio
- [Kling Audio](https://dev.pika.art/models/kling/kling-audio/video-to-audio) (Video to Audio, async). Spec: https://dev.pika.art/llms/kling/kling-audio/video-to-audio

### MiniMax

- [MiniMax H3](https://dev.pika.art/models/minimax/h3/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/minimax/h3/text-to-video
- [MiniMax H3](https://dev.pika.art/models/minimax/h3/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/minimax/h3/image-to-video
- [MiniMax H3](https://dev.pika.art/models/minimax/h3/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/minimax/h3/reference-to-video
- [Hailuo 2.3](https://dev.pika.art/models/minimax/hailuo-2.3/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/minimax/hailuo-2.3/image-to-video
- [Hailuo 2.3](https://dev.pika.art/models/minimax/hailuo-2.3/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/minimax/hailuo-2.3/text-to-video
- [Hailuo 2.3 Fast](https://dev.pika.art/models/minimax/hailuo-2.3-fast/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/minimax/hailuo-2.3-fast/image-to-video
- [MiniMax Music 3.0](https://dev.pika.art/models/minimax/minimax-music-3.0/text-to-audio) (Text to Audio, async). Spec: https://dev.pika.art/llms/minimax/minimax-music-3.0/text-to-audio
- [MiniMax Speech 2.8 HD](https://dev.pika.art/models/minimax/minimax-speech-2.8-hd/text-to-speech) (Text to Speech, async). Spec: https://dev.pika.art/llms/minimax/minimax-speech-2.8-hd/text-to-speech
- [MiniMax Speech 2.8 Turbo](https://dev.pika.art/models/minimax/minimax-speech-2.8-turbo/text-to-speech) (Text to Speech, async). Spec: https://dev.pika.art/llms/minimax/minimax-speech-2.8-turbo/text-to-speech

### Moonshot AI

- [Kimi K3](https://dev.pika.art/models/moonshotai/kimi-k3) (LLM, sync). Spec: https://dev.pika.art/llms/moonshotai/kimi-k3

### OpenAI

- [GPT Image 2](https://dev.pika.art/models/openai/gpt-image-2/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/openai/gpt-image-2/image-to-image
- [GPT Image 2](https://dev.pika.art/models/openai/gpt-image-2/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/openai/gpt-image-2/text-to-image
- [Whisper](https://dev.pika.art/models/openai/whisper/transcription) (Transcription, async). Spec: https://dev.pika.art/llms/openai/whisper/transcription
- [GPT-5.6 Sol](https://dev.pika.art/models/openai/gpt-5.6-sol) (LLM, sync). Spec: https://dev.pika.art/llms/openai/gpt-5.6-sol
- [OpenAI GPT-5.6 Terra](https://dev.pika.art/models/openai/gpt-5.6-terra) (LLM, sync). Spec: https://dev.pika.art/llms/openai/gpt-5.6-terra
- [OpenAI GPT-5.6 Luna](https://dev.pika.art/models/openai/gpt-5.6-luna) (LLM, sync). Spec: https://dev.pika.art/llms/openai/gpt-5.6-luna
- [GPT-5.5](https://dev.pika.art/models/openai/gpt-5.5) (LLM, sync). Spec: https://dev.pika.art/llms/openai/gpt-5.5

### Recraft

- [Recraft 4.1](https://dev.pika.art/models/recraft/recraft-4.1/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/recraft/recraft-4.1/text-to-image

### Sonilo

- [Sonilo v1.1 Music](https://dev.pika.art/models/sonilo/sonilo-v1.1-music/text-to-music) (Text to Music, async). Spec: https://dev.pika.art/llms/sonilo/sonilo-v1.1-music/text-to-music
- [Sonilo v1.1 Music](https://dev.pika.art/models/sonilo/sonilo-v1.1-music/video-to-music) (Video to Music, async). Spec: https://dev.pika.art/llms/sonilo/sonilo-v1.1-music/video-to-music
- [Sonilo v1.1 Music](https://dev.pika.art/models/sonilo/sonilo-v1.1-music/video-to-scored-video) (Video to Scored Video, async). Spec: https://dev.pika.art/llms/sonilo/sonilo-v1.1-music/video-to-scored-video
- [Sonilo v1.1 SFX](https://dev.pika.art/models/sonilo/sonilo-v1.1-sfx/sound-effects) (Text to Sound Effects, async). Spec: https://dev.pika.art/llms/sonilo/sonilo-v1.1-sfx/sound-effects
- [Sonilo v1.1 SFX](https://dev.pika.art/models/sonilo/sonilo-v1.1-sfx/video-to-sound-effects) (Video to Sound Effects, async). Spec: https://dev.pika.art/llms/sonilo/sonilo-v1.1-sfx/video-to-sound-effects

### Topaz Labs

- [Topaz Video Upscale](https://dev.pika.art/models/topaz/topaz-video-upscale/video-upscale) (Video Upscale, async). Spec: https://dev.pika.art/llms/topaz/topaz-video-upscale/video-upscale
- [Topaz Image Upscale](https://dev.pika.art/models/topaz/topaz-image-upscale/image-upscale) (Image Upscale, async). Spec: https://dev.pika.art/llms/topaz/topaz-image-upscale/image-upscale

### xAI

- [Grok Imagine Video 1.5](https://dev.pika.art/models/x-ai/grok-imagine-video-1.5/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-video-1.5/image-to-video
- [Grok Imagine Video](https://dev.pika.art/models/x-ai/grok-imagine-video/text-to-video) (Text to Video, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-video/text-to-video
- [Grok Imagine Video](https://dev.pika.art/models/x-ai/grok-imagine-video/image-to-video) (Image to Video, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-video/image-to-video
- [Grok Imagine Video](https://dev.pika.art/models/x-ai/grok-imagine-video/reference-to-video) (Reference to Video, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-video/reference-to-video
- [Grok Imagine Video](https://dev.pika.art/models/x-ai/grok-imagine-video/video-to-video) (Video to Video, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-video/video-to-video
- [Grok Imagine Image Quality](https://dev.pika.art/models/x-ai/grok-imagine-image-quality/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-image-quality/text-to-image
- [Grok Imagine Image Quality](https://dev.pika.art/models/x-ai/grok-imagine-image-quality/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-image-quality/image-to-image
- [Grok Imagine](https://dev.pika.art/models/x-ai/grok-imagine-image/text-to-image) (Text to Image, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-image/text-to-image
- [Grok Imagine](https://dev.pika.art/models/x-ai/grok-imagine-image/image-to-image) (Image to Image, async). Spec: https://dev.pika.art/llms/x-ai/grok-imagine-image/image-to-image

### Z.ai

- [GLM-5.2](https://dev.pika.art/models/z-ai/glm-5.2) (LLM, sync). Spec: https://dev.pika.art/llms/z-ai/glm-5.2