> ## Documentation Index > Fetch the complete documentation index at: https://docs.dualmindlab.tech/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > DualMind Arena API base URL: https://api.dualmindlab.tech. Public endpoints only; admin routes are not part of this API. > Authenticate with the access token from an Arena session (a Supabase JWT) as `Authorization: Bearer `. There are no API keys yet; never invent one. > For battles call POST /api/arena/dualchat, then vote with POST /api/arena/model-vote using the returned comparisonId. Keep model names hidden from voters until they vote. > GET /api/arena/model-stats (leaderboard) and GET /health need no token. # Chat with one model > Direct Chat: send a prompt to one model (or `auto` for a random one) and get the full reply. Direct Chat with one model. Set `model` to a `modelName` or `modelId` from [List models](/api-reference/models/list-models), or `auto` to get a random Groq or Google AI Studio model. Want text as it's generated? Use [Stream a chat reply](/api-reference/chat/streaming). ## OpenAPI ````yaml POST /api/arena/chat openapi: 3.1.0 info: title: DualMind Arena API version: 1.0.0 description: >- The REST API behind DualMind Arena: blind battles, votes, the leaderboard, models and threads. contact: name: DualMind Labs email: support@dualmindlab.tech url: https://dualmindlab.tech servers: - url: https://api.dualmindlab.tech description: Production security: - bearerAuth: [] tags: - name: Arena description: Battles and chat. - name: Voting description: Votes and the leaderboard. - name: Models description: Available models. - name: Threads description: Saved conversations and sharing. - name: Utilities description: Health and feature flags. paths: /api/arena/chat: post: tags: - Arena summary: Chat with one model description: >- Direct Chat: send a prompt to one model (or `auto` for a random one) and get the full reply. operationId: chat requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatRequest' example: prompt: Explain TCP vs UDP with a pizza analogy model: auto responses: '200': description: The model's reply. content: application/json: schema: $ref: '#/components/schemas/ChatResponse' example: object: ai.response output: type: message content: - type: output_text text: Packets are pizzas... success: true message: Packets are pizzas... model: name: llama-3.3-70b-versatile displayName: Llama 3.3 70B Versatile provider: groq prompt: Explain TCP vs UDP with a pizza analogy selectionMode: automatic responseTimeMs: 2140 usage: promptTokens: 18 completionTokens: 212 totalTokens: 230 timestamp: '2026-10-17T12:00:00Z' '400': description: Missing prompt. content: application/json: schema: $ref: '#/components/schemas/AiError' '401': $ref: '#/components/responses/Unauthorized' '500': description: Unexpected server error. content: application/json: schema: $ref: '#/components/schemas/AiError' security: - bearerAuth: [] components: schemas: ChatRequest: type: object required: - prompt properties: prompt: type: string description: The user prompt. Must not be empty. example: Explain TCP vs UDP with a pizza analogy model: type: string default: auto description: >- Model to use: a `modelName` (or `modelId`) from `GET /api/models`, or `auto` to let the Arena pick a random model. example: auto system: type: string description: Optional system prompt. maxTokens: type: integer minimum: 1 default: 4096 description: Maximum tokens to generate. temperature: type: number minimum: 0 maximum: 2 default: 0.7 description: Sampling temperature. threadId: type: string format: uuid description: Save the prompt and reply to this thread. You must own the thread. ChatResponse: type: object properties: object: type: string const: ai.response success: type: boolean message: type: string description: The model's reply as plain text (Markdown). output: type: object description: The same reply in a structured content envelope. properties: type: type: string const: message content: type: array items: type: object properties: type: type: string const: output_text text: type: string model: $ref: '#/components/schemas/ModelInfo' prompt: type: string selectionMode: type: string enum: - automatic - manual - random - topper description: >- `automatic`/`manual` for single chat; `random`/`topper`/`manual` for battles. responseTimeMs: type: integer description: >- Wall-clock time of the request in milliseconds. In a battle both models run in parallel, so this is the time until both finished. usage: $ref: '#/components/schemas/Usage' timestamp: type: string format: date-time AiError: type: object description: >- Error envelope used by the chat endpoints (and as an SSE event on the stream). properties: object: type: string const: ai.error code: type: string enum: - INVALID_REQUEST - API_ERROR - STREAM_ERROR message: type: string timestamp: type: string format: date-time ModelInfo: type: object properties: name: type: string description: >- Provider model name, e.g. `llama-3.3-70b-versatile` or `@cf/meta/llama-3.1-8b-instruct`. displayName: type: string description: Human-friendly name. provider: type: string enum: - groq - google - cloudflare description: Inference provider. Usage: type: object properties: promptTokens: type: integer completionTokens: type: integer totalTokens: type: integer responses: Unauthorized: description: >- Missing, invalid or expired token. The body is empty; the `WWW-Authenticate` header explains why. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- The access token from your DualMind Arena session (a Supabase JWT). See Authentication. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.