> ## Documentation Index > Fetch the complete documentation index at: https://lava.so/docs/llms.txt > Use this file to discover all available pages before exploring further. # List services > Returns a list of all models and API services available through the Lava gateway, including provider API reference URLs, pricing, capabilities, and managed/BYOK status. This endpoint is public and does not require authentication. ## OpenAPI ````yaml /openapi.json get /services openapi: 3.0.0 info: title: Lava API description: >- Lava API enables businesses to implement usage-based billing for AI services. This API allows tracking, managing, and billing for third-party AI API usage through a forwarding system. version: 1.0.0 contact: name: Lava support url: https://www.lava.so/contact servers: - url: https://api.lava.so/v1/ description: Lava API v1 security: [] tags: - name: Authentication - name: Core Endpoints - name: Models - name: Services - name: Requests - name: Wallet - name: Payment Methods - name: Spend Keys - name: Usage - name: Checkout Sessions - name: Customers - name: Plans - name: Subscriptions - name: Meters - name: Webhooks - name: Secret Keys - name: Credit Bundles - name: Gateway Settings - name: Skills - name: News Data - name: Search - name: Enrich paths: /services: get: tags: - Services summary: List services description: >- Returns a list of all models and API services available through the Lava gateway, including provider API reference URLs, pricing, capabilities, and managed/BYOK status. This endpoint is public and does not require authentication. parameters: - name: provider in: query required: false schema: type: string description: >- Optional provider identifier to return only one provider slice from the service catalog responses: '200': description: Full service catalog headers: Cache-Control: schema: type: string example: public, max-age=3600 description: Response is cached for 1 hour x-lava-request-id: schema: type: string description: Unique request identifier content: application/json: schema: type: object properties: object: type: string enum: - list data: type: array description: List of all available models and services items: $ref: '#/components/schemas/ServiceEntry' providers: type: array description: Summary of available providers items: $ref: '#/components/schemas/ServiceProvider' security: [] components: schemas: ServiceEntry: type: object description: A model or API service available through the Lava gateway. properties: id: type: string description: >- Unique identifier for the service (e.g., gpt-4o, claude-sonnet-4-6, serper-search) object: type: string enum: - model - service description: Whether this is an AI model or an API service provider: type: string description: Provider identifier (e.g., openai, anthropic, google, serper) provider_label: type: string description: Human-readable provider name (e.g., OpenAI, Anthropic, Google) api_reference: type: string nullable: true description: >- Official provider API reference URL for provider-native request shapes and endpoints endpoint: type: string description: >- Exact Lava-supported upstream endpoint pattern, including HTTP method method: type: string enum: - POST - GET - PUT - PATCH - DELETE description: HTTP method for the upstream endpoint url_template: type: string description: Upstream URL template without the HTTP method prefix workflow: type: object nullable: true properties: kind: type: string enum: - poll description: Workflow type required to complete the request poll_after: type: string description: >- Follow-up endpoint template agents should poll after the initial request id_field: type: string description: >- Response field name whose value should be inserted into the poll template required: - kind - poll_after - id_field description: Optional orchestration metadata for async or multi-step endpoints example_body: nullable: true oneOf: - type: object additionalProperties: true - type: array items: {} description: >- Minimal example request body for this catalog entry when one is available service_type: type: string enum: - model - service description: Whether this entry is an AI model or an API service managed: type: boolean description: >- Whether Lava provides managed access (true) or requires bring-your-own-key (false) pricing: $ref: '#/components/schemas/ServicePricing' capabilities: type: array items: type: string description: >- List of capabilities (e.g., chat, streaming, embeddings, image-generation, text-to-speech, web-search) required: - id - object - provider - provider_label - api_reference - endpoint - method - url_template - workflow - example_body - service_type - managed - pricing - capabilities ServiceProvider: type: object description: Summary of a provider in the service catalog. properties: id: type: string description: Provider identifier label: type: string description: Human-readable provider name api_reference: type: string nullable: true description: Official provider API reference URL service_type: type: string enum: - model - service description: Primary type of entries from this provider managed: type: boolean description: Whether Lava provides managed access for this provider entry_count: type: integer description: Number of entries (models or services) from this provider required: - id - label - api_reference - service_type - managed - entry_count ServicePricing: type: object description: >- Pricing information for a service entry. Structure varies by pricing type. properties: type: type: string enum: - tokens_1m - tokens_multimodal_1m - characters_1m - minutes - request - request_1m - free description: Pricing model type input: type: number description: >- Cost per 1M input units (tokens, characters, or requests). Present for token, character, and request_1m pricing types. output: type: number description: >- Cost per 1M output units. Present for token, character, and request_1m pricing types. cache_input_read: type: number description: >- Cost per 1M cached input tokens (read). Only present for tokens_1m when the model supports prompt caching. cache_input_write: type: number description: >- Cost per 1M cached input tokens (write). Only present for tokens_1m when the model supports prompt caching. cost_per_request: type: number description: Flat cost per request. Only present for request pricing type. text: type: object description: Text modality pricing. Only present for tokens_multimodal_1m. properties: input: type: number output: type: number audio: type: object description: Audio modality pricing. Only present for tokens_multimodal_1m. properties: input: type: number output: type: number image: type: object description: Image modality pricing. Only present for tokens_multimodal_1m. properties: input: type: number output: type: number required: - type ````