> ## Documentation Index > Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request. > Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance. > For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code. > The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust. > Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool. > Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md. # Make a decision > Evaluate typed questions against application state with supported decision models. Use the OpenAI-compatible format for new calls: `input` contains text or user messages with inline `input_image` parts, and `questions` is an ordered array of `predicate`, `choice`, or `score` questions. Answers use the same order, with optional names. Boolean choice values remain booleans. Hosted HTTPS image URLs work only on Base Labs models (Elephant-1, Mammoth-1 and Joey-1) and must be on Amazon S3, Google Cloud Storage or Azure Blob Storage; Luna accepts up to 128 inline images, while other providers impose their own limits. Explicit image detail and `safety_identifier` require an OpenAI route. Existing `state`, named question maps, `noul`, and `criteria` remain supported and return the original answer map. Together Tev requires that legacy format because it returns labels without probabilities. The legacy examples below remain valid. ```json theme={null} { "model": "openai/gpt-6-luna", "input": "I was charged twice for my order.", "questions": [{ "type": "choice", "name": "department", "instructions": "Which department should handle this?", "choices": [ { "value": "billing", "description": "Payments and refunds" }, { "value": "other", "description": "Everything else" } ] }] } ``` Use `POST /v1/decisions` when your application needs structured answers that code can consume directly. Supported models include TypeSafe Jev 1.13 (`typesafe/jev-1.13.0`), Together Tev1 4B Experimental (`together/tev1-4b-experimental`), and Respan Span-01 (`respan/span-01:free` and `respan/span-01`). The request contains: * `state`: a string, object, or array containing the information to evaluate. * `questions`: a map of named questions. Each question sets `type` to `noul`, `choice`, or `score` and includes `instructions`; supported types depend on the selected model. * `model`: the Phaseo model ID. Use `typesafe/jev-1.13.0` for Jev 1.13, or `typesafe/jev-latest` to follow the latest Jev release. Liquid D1 (`liquid-ai/d1:free`, also available as `liquid-ai/d1`) and Perplexity Decider 27B (`perplexity/decider-27b`) support all three question types. D1 is free during experimental early access. Decider costs \$0.04 per million input tokens, including image tokens; output tokens are free. Add a Perplexity provider credential in Phaseo to use Decider. Its image state uses PNG, JPEG, or WebP base64 data URLs; remote image URLs are unsupported. Each choice question accepts up to 255 options, and each score question accepts up to 10 levels. Check model availability before calling either model. Mercury Decide (`inception/mercury-decide`) supports predicate, choice, and score questions with text or JSON evidence. Choice questions accept up to 255 options; score questions accept up to 10 levels. Images, streaming, and tool calling are unsupported. Input is currently \$0.02 per million tokens under Inception's 50% promotion; output tokens are reported but free. Inception has not published a promotion end date. Check model availability and [current upstream pricing](https://docs.inceptionlabs.ai/get-started/models) before use. ```json theme={null} { "model": "inception/mercury-decide", "input": "Please refund the duplicate charge on my account.", "questions": [{ "type": "predicate", "name": "billing", "instructions": "Is this request about billing?" }] } ``` Microsoft Decision (`microsoft/microsoft-decision-1`) uses an Azure Foundry deployment and supports predicate, choice, and score questions with text or JSON evidence. Its input limit is 32,768 tokens. Published pricing is \$0.042 per million input tokens, with free output. Media, streaming, tools, `safety_identifier`, and `service_tier` are unsupported. Check model availability before calling it. See [Microsoft's guide](https://learn.microsoft.com/azure/foundry/foundry-models/how-to/use-foundry-models-microsoft-decision). ```json theme={null} { "model": "microsoft/microsoft-decision-1", "input": "The API returns 500 on every call.", "questions": [{ "type": "choice", "name": "team", "instructions": "Which team should handle this ticket?", "choices": [ { "value": "engineering", "description": "Bugs, errors, and outages" }, { "value": "support", "description": "How-to and account questions" } ] }] } ``` For Respan Span-01, `state` must be a conversation span with an `input` array of preceding messages and an `output` assistant message. Span-01 supports `noul` questions only. The `noul` answer is the probability that the behavior is present; `probabilities` also includes absent and not-observable probabilities. ```json theme={null} { "model": "respan/span-01:free", "state": { "input": [{ "role": "user", "content": "Please connect me to a person." }], "output": { "role": "assistant", "content": "I will connect you to support." } }, "questions": { "escalation": { "type": "noul", "instructions": "Does the assistant offer a human handoff?" } } } ``` `respan/span-01:free` is the free Lite model with a daily limit; Phaseo maps it to Respan's `span-01-free` API model ID. `respan/span-01` maps to Respan's `span-01-pro` API model ID and is billed by Respan at \$0.02 per million input tokens; output tokens are free. Span-01 is in early access, so Respan must enable access for your organization. Add your Respan API key as a Respan provider credential in Phaseo before calling these models. Answers use the same keys as `questions`. `choice` answers include the selected option, probabilities, and confidence; `noul` answers include a 0–1 probability; and `score` answers include a probability-weighted score, legend, probabilities, and confidence. For the Respan example, a response looks like this: ```json theme={null} { "answers": { "escalation": { "type": "noul", "noul": 0.73, "probabilities": { "true": 0.73, "false": 0.25, "not_observable": 0.02 } } } } ``` Jev supports mixing all three question types in one request; Span-01 supports `noul` questions only. See the [Quickstart](https://phaseo.app/docs/v1/quickstart.md) for copy-pasteable cURL, JavaScript, TypeScript SDK, and Python SDK examples. Jev 1.13 is billed at \$0.042 per 1M input tokens; output tokens are free. For the upstream question semantics, see TypeSafe's [API reference](https://docs.typesafe.ai/api). ### Images, Box, and long context with Jev On supporting TypeSafe routes, Jev 1.13 and 1.14 accept inline PNG or JPEG images through `input_image` or legacy `images`. Phaseo builds TypeSafe's image assets and enables image support automatically. Images must meet TypeSafe's [image limits](https://docs.typesafe.ai/images): at most 16 MiB each, dimensions from 256 to 1568 pixels, and at least 78,400 total pixels. TypeSafe validates dimensions and encoding; it does not resize rejected images. The mapped upstream JSON body is limited to 32 MiB. Image tokens use the normal input price. `box` is a separate question type for supporting routes such as Jev 1.14. It requires an image, takes no criteria, and returns one bounding box plus confidence. Its `top`, `bottom`, `left`, and `right` edges range from 0 to 1, measured from the top-left corner. Box always returns a rectangle; pair it with a `predicate` presence question when the target may be absent. With legacy images, refer to `images[0]`; with ordered input, refer to the first image or `[Image 0]`. See the [Box contract](https://docs.typesafe.ai/primitives/box). Set `provider_options.typesafe.long_context` to `true` to raise both the per-request and per-question context limits to 262k tokens. The defaults are 64k per request and 32k per question. Long context is opt-in and has the same token price. Images, Box, and long context are experimental upstream capabilities; check model availability before use. ```json theme={null} { "model": "typesafe/jev-1.14.0", "input": [{ "role": "user", "content": [{ "type": "input_image", "image_url": "data:image/png;base64," }] }], "questions": [ { "type": "predicate", "name": "visible", "instructions": "Is there a mug in the first image?" }, { "type": "box", "name": "mug", "instructions": "The mug in the first image" } ], "provider_options": { "typesafe": { "long_context": true } } } ``` ### Image decisions with Clef `cloudflare/clef` and `cloudflare/clef-flash` support all three question types and embedded images through Cloudflare Workers AI. Clef has a 65,536-token context window; Clef Flash has 24,576 tokens. Input costs $0.24 per million tokens for Clef and $0.038 for Clef Flash. ```json theme={null} { "model": "cloudflare/clef-flash", "state": "Inspect the attached product photo.", "images": [{ "content_type": "image/png", "base64": "" }], "questions": { "damaged": { "type": "noul", "instructions": "Is the product visibly damaged?" } } } ``` You can also supply a `data:image/png;base64,...` string in `images`. Clef accepts up to four PNG, JPEG, or WebP images, each at most 4 MiB and 16 megapixels, with at most 8 MiB of decoded image data and a 13 MiB request body. Remote URLs are unsupported. Cloudflare validates image formats and dimensions. Models without image support reject image requests. Clef accepts at most 64 questions, with IDs of up to 100 letters, digits, underscores, dots, or hyphens. Choice questions require 2–255 options; score questions require 2–10 levels. See Cloudflare's [Clef documentation](https://developers.cloudflare.com/workers-ai/models/clef/). ### Audio and video decisions with Clef Omni `cloudflare/clef-omni` accepts text, images, audio, and video with the same ordered `questions` and answers as other Decisions models. Audio and video are Phaseo extensions to the OpenAI-style input contract; OpenAI Decisions routes currently support text and images only. Check model availability before use. This example requires an available Omni route and a Phaseo API key. Replace the placeholder audio bytes and video URL with your own media before sending it. ```json theme={null} { "model": "cloudflare/clef-omni", "input": [{ "role": "user", "content": [ { "type": "input_text", "text": "Review the recording and clip." }, { "type": "input_audio", "input_audio": { "data": "", "format": "wav" } }, { "type": "input_video", "video_url": { "url": "https://media.example.com/clip.mp4" } } ] }], "questions": [{ "type": "predicate", "name": "safe", "instructions": "Is the equipment operating safely?" }] } ``` Use `input_audio.data` with `format: "wav"` or `"mp3"`, or `input_audio.url` with a public HTTPS URL or an inline audio data URL. `input_video.video_url` accepts a string or `{ "url": "..." }` containing a public HTTPS URL or an inline MP4/WebM data URL. Remote servers must return the matching media Content-Type. Phaseo fetches URLs with size limits and private-address/redirect checks, then embeds the media for Cloudflare; provider credentials are never sent to the media server. Omni accepts up to four audio clips (8 MiB and 300 seconds each) and two videos (16 MiB and 60 seconds each). Audio and video together cannot exceed 16 MiB decoded. Omni retains the per-image and combined-image limits above; its request-body limit replaces the 13 MiB Clef/Flash limit. Phaseo caps the complete Omni request body at 37 MiB. Cloudflare validates media encoding, image dimensions, and clip duration, and samples video at two frames per second. A video's soundtrack is used when every video in the request has one. Omni has a documented 64,000-token context and costs \$0.15 per million aggregate input tokens. Media tokens count toward context and billing; output is free. Phaseo settles against Cloudflare's reported input usage without adding separate audio or video charges. See [Cloudflare's Omni contract](https://github.com/cloudflare/cloudflare-docs/blob/production/src/content/workers-ai-models/clef-omni.json). ## OpenAPI ````yaml openapi/v1/openapi.yaml POST /decisions openapi: 3.0.3 info: title: Phaseo Gateway API description: >- A gateway API for accessing various AI models with OpenAI-compatible endpoints. version: 1.0.0 contact: name: Phaseo url: https://phaseo.app email: danielbutler500@gmail.com servers: - url: https://api.phaseo.app/v1 description: Global routing security: - BearerAuth: [] tags: - name: Gateway description: Core Phaseo Gateway operations. paths: /decisions: post: tags: - Gateway summary: Make structured decisions description: >- Evaluates ordered predicate, choice, and score questions against text or inline images using the OpenAI-compatible Decisions format. Legacy state and named question maps remain supported. operationId: makeDecision requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/DecisionCreateRequest' responses: '200': description: Structured decisions response content: application/json: schema: $ref: '#/components/schemas/DecisionCreateResponse' components: schemas: DecisionCreateRequest: description: >- OpenAI-compatible input and ordered questions are the preferred format. Legacy state and named question maps remain supported. The response format follows the request format; do not mix the two. oneOf: - $ref: '#/components/schemas/OpenAIDecisionsRequest' - $ref: '#/components/schemas/LegacyDecisionsRequest' DecisionCreateResponse: description: >- Ordered answers for input/array requests, or a named map for legacy state/map requests. oneOf: - $ref: '#/components/schemas/OpenAIDecisionsResponse' - $ref: '#/components/schemas/LegacyDecisionsResponse' OpenAIDecisionsRequest: type: object required: - model - input - questions properties: model: type: string minLength: 1 description: Canonical Phaseo model id or provider model alias. models: $ref: '#/components/schemas/ModelFallbacks' input: description: >- Text evidence or user messages containing text and inline images. Audio and video are Phaseo extensions for supporting models; OpenAI Decisions routes do not support these extensions. oneOf: - type: string maxLength: 10485760 - type: array items: $ref: '#/components/schemas/DecisionInputMessage' questions: type: array minItems: 1 items: oneOf: - $ref: '#/components/schemas/DecisionPredicateQuestion' - $ref: '#/components/schemas/OpenAIDecisionChoiceQuestion' - $ref: '#/components/schemas/OpenAIDecisionScoreQuestion' - $ref: '#/components/schemas/DecisionBoxQuestion' provider_options: $ref: '#/components/schemas/DecisionProviderOptions' safety_identifier: type: string nullable: true maxLength: 128 description: Opaque end-user identifier. Supported on OpenAI routes only. meta: type: boolean default: false echo_upstream_request: type: boolean debug: $ref: '#/components/schemas/DebugOptions' provider: $ref: '#/components/schemas/ProviderRoutingOptions' routing: $ref: '#/components/schemas/ProviderRoutingOptions' metadata: type: object additionalProperties: true LegacyDecisionsRequest: description: >- Compatibility format using state, named question maps, and noul questions. type: object required: - model - state - questions properties: model: type: string description: Canonical Phaseo model id or provider model alias. default: typesafe/jev-1.13.0 models: $ref: '#/components/schemas/ModelFallbacks' state: description: Structured state evaluated by the model. oneOf: - type: string - type: object additionalProperties: true - type: array items: {} questions: type: object minProperties: 1 maxProperties: 128 additionalProperties: oneOf: - $ref: '#/components/schemas/DecisionNoulQuestion' - $ref: '#/components/schemas/DecisionChoiceQuestion' - $ref: '#/components/schemas/DecisionScoreQuestion' - $ref: '#/components/schemas/LegacyDecisionBoxQuestion' provider_options: $ref: '#/components/schemas/DecisionProviderOptions' images: type: array maxItems: 4 description: >- Embedded images for vision-capable decision models. Clef accepts PNG, JPEG, or WebP; remote URLs are unsupported. Maximum 4 MiB and 16 megapixels per image, 8 MiB decoded total, and 13 MiB per request body. items: oneOf: - type: string pattern: >- ^[Dd][Aa][Tt][Aa]:image/(png|jpeg|webp);base64,[A-Za-z0-9+/]+={0,2}$ - $ref: '#/components/schemas/DecisionImage' meta: type: boolean default: false echo_upstream_request: type: boolean debug: $ref: '#/components/schemas/DebugOptions' provider: $ref: '#/components/schemas/ProviderRoutingOptions' routing: $ref: '#/components/schemas/ProviderRoutingOptions' metadata: type: object additionalProperties: true OpenAIDecisionsResponse: type: object required: - model - answers - usage properties: model: type: string answers: type: array description: >- One answer per question in request order, including unnamed or repeated-name questions. items: oneOf: - $ref: '#/components/schemas/DecisionPredicateAnswer' - $ref: '#/components/schemas/DecisionChoiceAnswer' - $ref: '#/components/schemas/DecisionScoreAnswer' - $ref: '#/components/schemas/DecisionRefusalAnswer' - $ref: '#/components/schemas/DecisionBoxAnswer' usage: $ref: '#/components/schemas/DecisionsUsage' request_id: type: string nullable: true meta: type: object additionalProperties: true LegacyDecisionsResponse: type: object properties: model: type: string answers: type: object additionalProperties: true usage: $ref: '#/components/schemas/DecisionsUsage' request_id: type: string nullable: true meta: type: object additionalProperties: true ModelFallbacks: type: array minItems: 1 maxItems: 25 items: type: string minLength: 1 description: >- Optional ordered fallback models tried after `model`. `model` is required and is always the primary model. When an attempt fails with `429`, `500`, `502`, `503`, or `504`, the next entry is tried; other errors are returned unchanged. Accepts up to 25 model IDs or presets; duplicates and entries equal to `model` are ignored. Each attempt is validated, logged, and billed as its own request, and the response `model` field and routing trace show the model that served the request. Streaming requests fall back only before the first byte, and video and music jobs fall back only at submission. Batch, realtime, and council requests reject `models`. Fallbacks set on a dynamic route take precedence, and `phaseo/auto` cannot be combined with `models`. example: - anthropic/claude-sonnet-5-5 - google/gemini-2.5-flash DecisionInputMessage: type: object required: - role - content additionalProperties: false properties: type: type: string enum: - message role: type: string enum: - user content: oneOf: - type: string maxLength: 10485760 - type: array items: oneOf: - $ref: '#/components/schemas/DecisionInputText' - $ref: '#/components/schemas/DecisionInputImage' - $ref: '#/components/schemas/DecisionInputAudio' - $ref: '#/components/schemas/DecisionInputVideo' DecisionPredicateQuestion: type: object required: - type - instructions additionalProperties: false properties: type: type: string enum: - predicate name: type: string maxLength: 1048576 instructions: type: string maxLength: 1048576 OpenAIDecisionChoiceQuestion: type: object required: - type - instructions - choices additionalProperties: false properties: type: type: string enum: - choice name: type: string maxLength: 1048576 instructions: type: string maxLength: 1048576 choices: type: array minItems: 1 description: >- Values must be distinct; a boolean and a string with the same text are different values. items: type: object required: - value additionalProperties: false properties: value: oneOf: - type: string - type: boolean description: type: string maxLength: 1048576 OpenAIDecisionScoreQuestion: type: object required: - type - instructions - levels additionalProperties: false properties: type: type: string enum: - score name: type: string maxLength: 1048576 instructions: type: string maxLength: 1048576 levels: type: array minItems: 1 items: type: object required: - label additionalProperties: false properties: label: type: string maxLength: 1048576 description: type: string maxLength: 1048576 DecisionBoxQuestion: type: object required: - type - instructions additionalProperties: false description: >- Phaseo extension for a single bounding box. Requires image input and a supporting route, such as Jev 1.14. No criteria or not-found result. properties: type: type: string enum: - box name: type: string maxLength: 1048576 instructions: type: string maxLength: 1048576 DecisionProviderOptions: type: object properties: typesafe: type: object additionalProperties: false properties: long_context: type: boolean description: >- Opt in to experimental Jev long context: 262k tokens per request and per question, instead of 64k per request and 32k per question. Default false. Requires a supporting TypeSafe route. DebugOptions: type: object description: Gateway debug controls. These flags are never forwarded upstream. properties: enabled: type: boolean return_upstream_request: type: boolean return_upstream_response: type: boolean trace: type: boolean trace_level: type: string enum: - summary - full ProviderRoutingOptions: type: object description: Provider routing preferences for gateway selection. properties: order: type: array items: type: string only: type: array items: type: string ignore: type: array items: type: string include_alpha: type: boolean description: Include alpha providers in routing (off by default). allow_fallbacks: type: boolean nullable: true description: Allow fallback to another eligible provider after failure. require_parameters: type: boolean nullable: true description: Require provider support for requested parameters before routing. required_execution_region: type: string nullable: true description: Restrict routing to providers with the requested execution region. required_data_region: type: string nullable: true description: Restrict routing to providers with the requested data region. require_zero_data_retention: type: boolean nullable: true description: Restrict routing to providers that support zero data retention. data_collection: type: string nullable: true description: >- `allow` (the default) filters nothing. `deny` is not supported yet and returns 400 unsupported_routing_filter. enum: - allow - deny zdr: type: boolean nullable: true enforce_distillable_text: type: boolean nullable: true description: >- `false` (the default) filters nothing. `true` is not supported yet and returns 400 unsupported_routing_filter. quantizations: type: array nullable: true items: type: string sort: oneOf: - type: string - type: object additionalProperties: true description: >- Rank providers for this request, for example by price, latency, or throughput. max_price: type: object properties: prompt: oneOf: - type: number - type: string completion: oneOf: - type: number - type: string image: oneOf: - type: number - type: string audio: oneOf: - type: number - type: string request: oneOf: - type: number - type: string preferred_min_throughput: oneOf: - type: number - type: object additionalProperties: type: number preferred_max_latency: oneOf: - type: number - type: object additionalProperties: type: number DecisionNoulQuestion: type: object required: - type - instructions properties: type: type: string enum: - noul instructions: $ref: '#/components/schemas/DecisionInstructions' criteria: type: object properties: 'true': type: string 'false': type: string additionalProperties: true DecisionChoiceQuestion: type: object required: - type - instructions - criteria properties: type: type: string enum: - choice instructions: $ref: '#/components/schemas/DecisionInstructions' criteria: type: object minProperties: 1 additionalProperties: type: string nullable: true DecisionScoreQuestion: type: object required: - type - instructions - criteria properties: type: type: string enum: - score instructions: $ref: '#/components/schemas/DecisionInstructions' criteria: type: array minItems: 2 items: type: string LegacyDecisionBoxQuestion: type: object required: - type - instructions additionalProperties: false description: Single bounding-box question for image-capable Box routes. No criteria. properties: type: type: string enum: - box instructions: $ref: '#/components/schemas/DecisionInstructions' DecisionImage: type: object required: - content_type - base64 properties: content_type: type: string enum: - image/png - image/jpeg - image/webp base64: type: string pattern: ^[A-Za-z0-9+/]+={0,2}$ DecisionPredicateAnswer: type: object required: - type - name - probability properties: type: type: string enum: - predicate name: type: string nullable: true probability: type: number minimum: 0 maximum: 1 DecisionChoiceAnswer: type: object required: - type - name - choice - probabilities - confidence properties: type: type: string enum: - choice name: type: string nullable: true choice: oneOf: - type: string - type: boolean confidence: type: number minimum: 0 maximum: 1 probabilities: type: array items: type: object required: - value - probability properties: value: oneOf: - type: string - type: boolean probability: type: number minimum: 0 maximum: 1 DecisionScoreAnswer: type: object required: - type - name - score - probabilities - confidence properties: type: type: string enum: - score name: type: string nullable: true score: type: number minimum: 0 confidence: type: number minimum: 0 maximum: 1 probabilities: type: array items: type: object required: - value - label - probability properties: value: type: integer minimum: 0 label: type: string probability: type: number minimum: 0 maximum: 1 DecisionRefusalAnswer: type: object required: - type - name properties: type: type: string enum: - refusal name: type: string nullable: true DecisionBoxAnswer: type: object required: - type - name - box - confidence properties: type: type: string enum: - box name: type: string nullable: true box: $ref: '#/components/schemas/DecisionBox' confidence: type: number minimum: 0 maximum: 1 nullable: true description: >- Confidence in the box, from 0 to 1, or null when the model gives none. DecisionsUsage: type: object properties: input_tokens: type: integer minimum: 0 output_tokens: type: integer minimum: 0 total_tokens: type: integer minimum: 0 input_tokens_details: type: object properties: cached_tokens: type: integer minimum: 0 cache_write_tokens: type: integer minimum: 0 output_tokens_details: type: object properties: reasoning_tokens: type: integer minimum: 0 DecisionInputText: type: object required: - type - text additionalProperties: false properties: type: type: string enum: - input_text text: type: string maxLength: 10485760 DecisionInputImage: type: object required: - type - image_url additionalProperties: false description: >- Inline base64 image, or an HTTPS image URL on Amazon S3, Google Cloud Storage or Azure Blob Storage (Base Labs models only). File IDs are unsupported. A request supports at most 128 images across all messages; individual providers can impose lower limits. properties: type: type: string enum: - input_image image_url: type: string maxLength: 1073741824 pattern: >- ^(data:image/[a-zA-Z0-9.+-]+;base64,[A-Za-z0-9+/]+={0,2}|https://\S+)$ detail: type: string nullable: true enum: - low - high - auto - original description: Explicit image detail is supported on OpenAI routes only. DecisionInputAudio: type: object required: - type - input_audio additionalProperties: false description: >- Phaseo extension for audio-capable decision models such as Clef Omni. Supply exactly one of base64 data (with format) or a public HTTPS/inline audio data URL. OpenAI decision models do not support this extension. properties: type: type: string enum: - input_audio input_audio: $ref: '#/components/schemas/DecisionAudioSource' DecisionInputVideo: type: object required: - type - video_url additionalProperties: false description: >- Phaseo extension for video-capable decision models such as Clef Omni. Supply a public HTTPS URL or an inline video data URL. OpenAI decision models do not support this extension. properties: type: type: string enum: - input_video video_url: oneOf: - type: string maxLength: 25165824 pattern: >- ^(https://|data:video/[a-zA-Z0-9.+-]+;base64,[A-Za-z0-9+/]+={0,2}$) - type: object required: - url additionalProperties: false properties: url: type: string maxLength: 25165824 pattern: >- ^(https://|data:video/[a-zA-Z0-9.+-]+;base64,[A-Za-z0-9+/]+={0,2}$) DecisionInstructions: oneOf: - type: string - type: object additionalProperties: true - type: array items: {} DecisionBox: type: object required: - top - bottom - left - right description: >- Edges as fractions of image dimensions from the top-left corner. top must be less than bottom; left must be less than right. properties: top: type: number minimum: 0 maximum: 1 bottom: type: number minimum: 0 maximum: 1 left: type: number minimum: 0 maximum: 1 right: type: number minimum: 0 maximum: 1 DecisionAudioSource: type: object additionalProperties: false anyOf: - required: - data - format - required: - url not: required: - data - url properties: data: type: string maxLength: 12582912 pattern: ^[A-Za-z0-9+/]+={0,2}$ format: type: string enum: - wav - mp3 url: type: string maxLength: 25165824 pattern: ^(https://|data:audio/[a-zA-Z0-9.+-]+;base64,[A-Za-z0-9+/]+={0,2}$) securitySchemes: BearerAuth: type: http scheme: bearer description: Bearer token authentication ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.