> ## Documentation Index > Fetch the complete documentation index at: https://omnirelay.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List models > Returns callable real models filtered by workspace, key allowlist and available runtime/channels. Use your own response for IDs, capabilities, limits, reasoning efforts and prices. Catalog visibility does not grant access. ## OpenAPI ````yaml /openapi.json get /v1/models openapi: 3.1.0 info: title: OmniRelay API version: 1.0.0 description: >- OpenAI-compatible gateway for reviewed real text models. Access is workspace-specific; query your own model list for capabilities and customer prices. servers: - url: https://api.omnirelay.ai security: - bearerAuth: [] tags: - name: Service - name: Models - name: Chat - name: Management - name: Responses - name: Embeddings - name: Images - name: Videos paths: /v1/models: get: tags: - Models summary: List models description: >- Returns callable real models filtered by workspace, key allowlist and available runtime/channels. Use your own response for IDs, capabilities, limits, reasoning efforts and prices. Catalog visibility does not grant access. operationId: listModels responses: '200': description: Active models. content: application/json: schema: $ref: '#/components/schemas/ModelList' example: object: list data: - id: gpt-5.4-mini object: model owned_by: OpenAI name: GPT 5.4 Mini mode: live context_length: 400000 capabilities: text: true stream: true system: true developer: false reasoning_content: false tools: true vision: false structured_output: true json_object: true json_schema: true responses: true embeddings: false pricing_unit: micro-USD / 1M tokens pricing: input: 750000 output: 4500000 list_pricing: input: 750000 output: 4500000 discount: 0 limits: output_tokens: 256 default_output_tokens: 64 reasoning_efforts: - none default_reasoning_effort: none '401': $ref: '#/components/responses/Unauthorized' components: schemas: ModelList: type: object required: - object - data properties: object: type: string enum: - list data: type: array items: $ref: '#/components/schemas/Model' Model: type: object required: - id - object - owned_by properties: id: type: string description: Model ID to pass as `model`. example: gpt-6-luna object: type: string enum: - model owned_by: type: string description: Provider the model is attributed to. example: OpenAI name: type: string description: Display name. example: GPT 5.4 Mini context_length: type: integer description: Context window in tokens. example: 400000 mode: type: string enum: - live description: 'live: the model calls a real provider.' capabilities: type: object description: >- Documented capability guidance. With parameter_policy=upstream-first, false is not a local ordinary-parameter rejection rule; the model provider decides support. Platform protocol and billing boundaries still apply. additionalProperties: type: boolean pricing_unit: type: string description: Unit of every price below. example: micro-USD / 1M tokens pricing: $ref: '#/components/schemas/ModelPrice' description: >- Customer input/output base rates. Round the full charge, then apply customer_discount_bps; rates are not pre-discounted. list_pricing: $ref: '#/components/schemas/ModelPrice' description: The price before any discount. discount: type: number minimum: 0 maximum: 1 description: >- Share taken off the list price for this workspace and model: `0.2` means 20% off, `0` means none. example: 0 context_verified: type: boolean description: Whether the runtime context contract is verified. context_basis: type: string enum: - input-plus-output description: >- Physical joint input/output context; independent fee bounds do not enlarge this window. max_input_tokens: type: - integer - 'null' description: Reviewed provider input ceiling, not measured prompt tokens. limits: type: object additionalProperties: type: integer description: >- Gateway runtime limits: output_tokens is the maximum and default_output_tokens is the omitted-field default. GPT 5.4 Mini: 64/256; most other integrated text routes: 32,000 default, up to 128,000 (Gemini 3.1 Pro Preview and Gemini 3.6 Flash: 65,536); DeepSeek V4 Pro, GLM 5.3 and Kimi K3: 4,096/4,096. request_bytes is the request body limit in UTF-8 bytes, messages the maximum message count and message_characters the maximum length of one text value; the model context window still applies. reasoning_efforts: type: array items: type: string description: >- Allowed Chat reasoning_effort values. Empty means unsupported. Responses uses responses_reasoning_efforts; tools/sampling have separate combination constraints. default_reasoning_effort: type: - string - 'null' description: >- Reviewed effort injected when omitted; null when no default effort is configured. token_budget_mode: type: string enum: - provider-context-ceiling description: >- Caps the reserved input at a provider input ceiling instead of claiming locally counted prompt context fit. input_bound_basis: type: string enum: - provider-enforced-input-ceiling description: >- Reserved input is an estimate: a third of the request byte length plus 4096 tokens of fixed overhead, capped by the provider-enforced input ceiling. Not a token count; settlement may exceed the hold by up to twice when funds cover it. context_fit_validation: type: string enum: - provider description: >- The model provider decides actual context fit. A post-dispatch rejection can keep a pending hold. reservation_basis: type: string enum: - independent-input-output-ceilings description: >- Reserves an input bound and the requested output separately. Initial input ceiling 400000 and output cap 256; the maximum hold depends on current workspace prices and is not a fixed fee. price_version: type: string description: Frozen customer price-contract version. customer_discount_bps: type: integer minimum: 0 maximum: 10000 description: >- Live request price factor: 10000 full price; apply after full-request rounding. customer_discount_source: type: string enum: - workspace - model description: Model discount replaces the workspace discount, never stacks. cache_pricing: type: - object - 'null' properties: read: type: integer minimum: 0 write: type: integer minimum: 0 unit: type: string description: Customer cache base rates before request discount. reasoning_price: type: integer minimum: 0 description: >- Customer reasoning-output base rate, in micro-USD per million tokens. request_fee_microusd: type: integer minimum: 0 description: >- Customer fixed request fee before discount; zero on the initial model provider endpoint. tier_mode: type: - string - 'null' description: Input tier selection policy where supported. input_tiers: type: array items: type: object properties: min_input_tokens: type: integer minimum: 0 input: type: integer minimum: 0 output: type: integer minimum: 0 cache_read: type: integer minimum: 0 cache_write: type: integer minimum: 0 reasoning: type: integer minimum: 0 request_fee_microusd: type: integer minimum: 0 description: Whole-request customer base-rate bands, before customer discount. reservation: type: object description: >- Customer holds in micro-USD: the shortest request with one output token (minimum) and with default output (default), and a request at the input ceiling with maximum output (maximum). A longer prompt holds more. These are pre-dispatch reservations at current customer prices, not settled fees. properties: currency: type: string enum: - USD unit: type: string enum: - micro-USD minimum_customer_hold: type: integer minimum: 0 default_customer_hold: type: integer minimum: 0 maximum_customer_hold: type: integer minimum: 0 responses_reasoning_efforts: type: array items: type: string description: Allowed Responses reasoning.effort values. sampling_parameters: type: array items: type: string description: Allowed sampling parameter names. sampling_reasoning_efforts: type: - array - 'null' items: type: string description: >- Efforts compatible with sampling; null means no additional restriction. chat_tools_reasoning_efforts: type: - array - 'null' items: type: string description: >- Efforts compatible with Chat tools/history; null means no additional restriction. tool_choice_values: type: array items: type: string description: Allowed string tool_choice values. tool_choice_reasoning_efforts: type: - array - 'null' items: type: string description: >- Efforts compatible with required/named tool choice; null means no additional restriction. thinking_modes: type: array items: type: string description: Allowed thinking.type values. parameter_ranges: type: object additionalProperties: type: array minItems: 2 maxItems: 2 items: type: number description: Model-specific inclusive minimum/maximum ranges. parameter_policy: type: string enum: - upstream-first - reviewed description: >- upstream-first forwards ordinary fields and the model provider decides on them, possibly ignoring unsupported ones; platform funding/protocol checks remain. capability_basis: type: string description: Evidence basis of the published capability guidance. Error: type: object required: - error properties: error: type: object required: - code - message - type properties: code: type: string example: model_unavailable message: type: string example: The model does not exist or is disabled. description: >- Short English description for logs and SDK exceptions. Its wording can change; branch on code. type: type: string example: not_found_error description: >- Error family by HTTP status: invalid_request_error, authentication_error, insufficient_quota, permission_error, not_found_error, conflict_error, rate_limit_error, service_unavailable or api_error. param: type: string maxLength: 200 description: >- Rejected request field path when identifiable; never a parameter value. Responses uses native field names. request_id: type: string description: Present on chat completion, Responses and embeddings errors. ModelPrice: type: object required: - input - output properties: input: type: integer description: Price of input tokens. example: 2500000 output: type: integer description: Price of output tokens. example: 10000000 responses: Unauthorized: description: '`unauthorized`: the API key is missing, revoked, or invalid.' content: application/json: schema: $ref: '#/components/schemas/Error' example: error: code: unauthorized securitySchemes: bearerAuth: type: http scheme: bearer description: >- An API key created in the OmniRelay console. The owner can view it again in the console after confirming their identity. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.