Eden AI API V3
The current Eden AI gateway: OpenAI-compatible chat completions, responses, embeddings, moderations, images and audio, an Anthropic Messages pass-through, the model-routed Universal AI expert-model endpoint (sync and async), collections and persistent file storage. 37 operations in the first-party OpenAPI 3.1.0 served at https://api.edenai.run/v3/docs/openapi.json.
Eden AI API V3 is one of 13 APIs that Eden AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Artificial Intelligence, AI Gateway, LLM, Chat Completions, and Embeddings. The published artifact set on APIs.io includes an OpenAPI specification and an API reference.
This API exposes
37 operations
across 29 paths,
organized into 12 resource areas,
and defines 87 schemas.
It is described by OpenAPI 3.1.0, at version 3.0.0.
Requests are made against a single base URL, https://api.edenai.run.
The identity and technical contract details declared by the specification.
AddItemRequest
object
Body for adding an item to a collection.
1 property
1 required
AnthropicContentBlock
object
11 properties
1 required
AnthropicCountTokensBody
object
Body for /v1/messages/counttokens — same fields as messages but maxtokens is optional.
5 properties
2 required
AnthropicCountTokensResponse
object
Response body for POST /v1/messages/counttokens.
1 property
1 required
AnthropicMessage
object
3 properties
2 required
AnthropicMessagesBody
object
18 properties
2 required
AnthropicMessagesResponse
object
Response body for POST /v1/messages (non-streaming).
8 properties
4 required
AnthropicUsage
object
Token usage block returned by the Anthropic Messages API.
4 properties
2 required
Body_upload_file_v3_upload_post
object
3 properties
1 required
CacheControl
object
Prompt-cache marker. Marks a message (or content part) as a cache boundary so that the prefix up to that point is stored and reused on subsequent requests, red…
2 properties
1 required
Capabilities
object
Model capability flags. Unknown flags are preserved so consumers keep working when new capabilities are introduced without a coordinated release.
14 properties
ChatCompletionChoice
object
A single choice in a chat completion response.
4 properties
2 required
ChatCompletionMessage
object
Message returned in a chat completion choice.
5 properties
ChatCompletionResponse
object
Response body for POST /chat/completions (non-streaming).
8 properties
4 required
ChatCompletionUsage
object
Token usage block returned by the OpenAI-compatible chat completion API.
5 properties
3 required
CollectionResponse
object
A collection owned by the authenticated user.
3 properties
2 required
CreateCollectionRequest
object
Body for creating a collection.
2 properties
1 required
DeleteCollectionResponse
object
Result of deleting a collection.
2 properties
2 required
DeleteFilesRequest
object
Request body for deleting multiple files.
1 property
1 required
DeleteFilesResponse
object
Response for file deletion.
1 property
1 required
DeleteItemResponse
object
Result of deleting an item from a collection.
3 properties
3 required
DeleteResponseObject
object
3 properties
2 required
EasyInputMessage
object
6 properties
2 required
EmbeddingItem
object
OpenAI embedding item with the wire-format quirk made explicit. The OpenAI SDK types embedding as list[float] only because the SDK transparently decodes base64…
3 properties
3 required
EmbeddingsBody
object
OpenAI-compatible POST /v1/embeddings request body, plus minimal Eden extensions. Unknown top-level fields are forwarded to the underlying provider (extra="all…
7 properties
2 required
EmbeddingsResponse
object
OpenAI-compatible embeddings response + Eden cost and provider fields. EmbeddingsDataClass (from edenai-apis) already widens data[].embedding to list[float] |…
6 properties
4 required
FeatureInfo
object
Info about a feature and its subfeatures.
4 properties
3 required
FeaturesListResponse
object
Response for listing all features.
1 property
1 required
FileResponse
object
Response for a file.
8 properties
6 required
GeminiImageConfig
object
Image generation config for Gemini image models (google/gemini-2.5-flash-image). Values are passed through to Gemini's generationConfig.imageConfig. Allowed va…
2 properties
HTTPValidationError
object
1 property
ImageDataItem
object
Single image entry inside the OpenAI-shaped data: [...] array. Providers return either url (most non-OpenAI providers) or b64json (gpt-image-); revisedprompt i…
3 properties
ImageGenerationBody
object
OpenAI-compatible POST /v1/images/generations request body.
10 properties
2 required
ImageResponse
object
OpenAI-compatible image response + Eden cost / provider fields. Shared by POST /v3/images/generations and POST /v3/images/edits — the wire shape is identical.
5 properties
ItemsResponse
object
Item ids stored in a collection (provider-side ids, passed through).
2 properties
2 required
LLMResponseObject
object
13 properties
5 required
ListCollectionsResponse
object
Paginated list of the user's collections.
5 properties
5 required
ListFilesResponse
object
Response for listing files with pagination.
5 properties
5 required
ListModelsResponse
object
List models response.
2 properties
1 required
ListModelsWithEndpointsResponse
object
?view=models response: routable names, each with its provider endpoints. Named for the public vocabulary rather than the internal one: Pydantic class names bec…
2 properties
1 required
LlmCompletionBody
object
44 properties
2 required
Message
object
3 properties
1 required
MessageAudioContent
object
4 properties
2 required
MessageAudioInput
object
2 properties
1 required
MessageFileB64Input
object
1 property
1 required
MessageFileContent
object
4 properties
2 required
MessageFileUrlInput
object
1 property
1 required
MessageImageContent
object
4 properties
2 required
MessageImageUrl
object
1 property
1 required
MessageRefusalContent
object
4 properties
2 required
MessageTextContent
object
4 properties
2 required
ModelObject
object
Extended model object with full metadata.
14 properties
4 required
ModelWithEndpoints
object
One routable model name and the provider endpoints behind it. Deliberately carries NO pricing, context window or capability of its own. Those vary between the…
7 properties
3 required
ModerationBody
object
2 properties
1 required
ModerationImageInput
object
2 properties
2 required
ModerationImageUrl
object
1 property
1 required
ModerationResponse
object
5 properties
3 required
ModerationTextInput
object
2 properties
2 required
OpenAIModerationResult
object
4 properties
4 required
PromptCacheBreakpoint
object
Marks the end of a reusable prompt prefix (OpenAI GPT-5.6 and newer). Set it on the last content part of the stable prefix you want cached: the prompt up to an…
1 property
PromptCacheOptions
object
Request-level prompt-cache settings (OpenAI GPT-5.6 and newer). Controls how this request's prompt cache behaves — whether caching happens automatically or onl…
2 properties
ProviderRoutingPreferences
object
How to choose between SELLERS of one model — and, with @edenai, how far to trade quality for cost when the platform chooses the model. The seller fields are on…
5 properties
RegionObject
object
Region where a model is available.
2 properties
2 required
ResponseInputFile
object
7 properties
1 required
ResponseInputImage
object
6 properties
1 required
ResponseInputItem
object
Non-message input item forwarded to the provider as-is (reasoning, functioncall, etc.).
2 properties
1 required
ResponseInputText
object
4 properties
2 required
ResponseOutputMessage
object
5 properties
5 required
ResponseOutputRefusal
object
2 properties
2 required
ResponseOutputText
object
3 properties
2 required
ResponseUsage
object
5 properties
3 required
ResponsesBody
object
26 properties
1 required
SchemaFormat
string
Output format for schema information.
SpeechBody
object
OpenAI-compatible text-to-speech request. Synthesizes input text into audio with the given voice. Unknown top-level fields are dropped.
7 properties
3 required
SubfeatureDetailResponse
object
Detailed response for a specific subfeature.
10 properties
9 required
SubfeatureInfo
object
Info about a subfeature.
5 properties
3 required
TranscriptionResponse
object
OpenAI-compatible transcription response, plus Eden cost / provider. The provider's full transcript payload passes through — text plus any language, duration,…
4 properties
UniversalAIAsyncBody
object
Universal AI async request body. Extends UniversalAIBody with webhook parameters for async notifications.
7 properties
2 required
UniversalAIAsyncJobListItem
object
Summary item for job list.
7 properties
6 required
UniversalAIAsyncJobListResponse
object
Response for listing async jobs.
5 properties
5 required
UniversalAIAsyncResponse
object
Async response from universal-ai/async endpoint. Inherits base fields and adds job-specific fields for tracking async operations. Used for both job creation (2…
11 properties
7 required
UniversalAIBody
object
Universal AI request body. Model format: feature/subfeature/provider[/model] Examples: - text/aidetection/openai/gpt-4 - ocr/ocr/amazon - image/generation/goog…
5 properties
2 required
UniversalAIResponse
object
Sync response from universal-ai endpoint. Inherits all fields from base, with status restricted to success/fail.
8 properties
6 required
UploadResponse
object
Response for a successful file upload.
8 properties
6 required
Usage
object
The usage information for the request.
2 properties
2 required
ValidationError
object
3 properties
3 required
ImageRef
object
One entry in images[] (or the mask value). Exactly one of fileid or imageurl must be set.
2 properties
The full machine-readable OpenAPI contract behind this narrative.
Other APIs Eden AI publishes across the network.
