> ## Documentation Index > Fetch the complete documentation index at: https://docs.x402layer.cc/llms.txt > Use this file to discover all available pages before exploring further. # Create a message (Anthropic) > Anthropic Messages API on Grid models. Works with the official Anthropic SDKs and Claude Code by setting the base URL to `https://grid.x402compute.cc`. Same auth, x402 payment, routing and billing as `/v1/chat/completions`. `?beta=true` is accepted. Unsupported features (extended thinking with a budget, structured outputs, server tools, documents, image URLs, `top_p`, `top_k`, prefill, unknown fields) return `400 invalid_request_error`. See the [Anthropic API guide](/cloud/grid/anthropic-api). ## OpenAPI ````yaml POST /v1/messages openapi: 3.1.0 info: title: x402 Singularity Layer API description: >- OpenAPI-backed reference for marketplace discovery, payment routes, webhooks, wallet-first auth, agent endpoints, and ERC-8004 flows. version: 1.0.0 servers: - url: https://api.x402layer.cc security: [] tags: - name: Marketplace description: Public discovery and listing lookup - name: Public Endpoints description: Public endpoint metadata and hosted checkout context - name: Public Payment Links description: Hosted public payment-link lookup - name: Payments description: Hosted x402 payment challenge routes - name: Receipts description: Signed receipt lookup and verification helpers - name: Ratings description: Public listing ratings and authenticated rating actions - name: Webhooks description: Seller webhook management API - name: Agent Auth description: Wallet-first challenge and verification routes - name: Agent Endpoints description: Create, read, top up, and delete agent endpoints - name: ERC-8004 description: Agent registry and registration lifecycle routes - name: Marketplace Agents description: Public ERC-8004 marketplace discovery routes - name: Compute Catalog description: Compute plans, regions, and OS catalog - name: Compute Instances description: Provision, inspect, extend, and destroy compute instances - name: Compute API Keys description: API keys for compute agent access - name: Fundraiser Campaigns description: List, view, create, and edit fundraiser campaigns - name: Fundraiser Contributions description: Record and list campaign contributions - name: Fundraiser Comments description: Campaign comment threads - name: Fundraiser Media description: Campaign image uploads and OG images - name: Enterprise description: >- Enterprise partner configuration, endpoint listing, revenue stats, and transaction ledger - name: Staking description: Agentic $SGL staking - name: SGL Grid description: >- Decentralized, confidential, OpenAI-compatible inference served by attested TEE nodes. - name: Compute Credits description: Prepaid USDC credit balance shared across Machines and Grid. - name: Agent Pods description: >- Deploy and manage hosted agents (Agent Pods), plus the pod's OpenAI-compatible adapter for external clients. - name: Agent Pods API description: >- The programmatic `/pods/v1` surface: create, drive and destroy Agent Pods with a single `X-API-Key`. Distinct from the Agent Pods dashboard routes, which expect a wallet signature or a browser session. paths: /v1/messages: servers: - url: https://grid.x402compute.cc post: tags: - SGL Grid summary: Create a message (Anthropic) description: >- Anthropic Messages API on Grid models. Works with the official Anthropic SDKs and Claude Code by setting the base URL to `https://grid.x402compute.cc`. Same auth, x402 payment, routing and billing as `/v1/chat/completions`. `?beta=true` is accepted. Unsupported features (extended thinking with a budget, structured outputs, server tools, documents, image URLs, `top_p`, `top_k`, prefill, unknown fields) return `400 invalid_request_error`. See the [Anthropic API guide](/cloud/grid/anthropic-api). parameters: - name: x-api-key in: header required: false schema: type: string example: x402c_... description: >- Singularity Layer compute API key, billed to credits. `Authorization: Bearer x402c_...` or a session token also work. Omit to pay per request with x402 `X-Payment`. - name: anthropic-version in: header required: false schema: type: string example: '2023-06-01' description: Accepted, not enforced. requestBody: required: true content: application/json: schema: type: object required: - model - messages - max_tokens properties: model: type: string example: qwen-2.5-32b description: >- A Grid model id from `GET /v1/models`, never a Claude model id. max_tokens: type: integer minimum: 1 example: 512 description: >- Lowered to fit the room left in the model's context. Output is capped at 8192. messages: type: array description: >- Conversation turns, `user` and `assistant`. Must not end with an assistant message (no prefill). A mid-conversation `system` message is folded into the user turn it follows. items: type: object required: - role - content properties: role: type: string enum: - user - assistant content: oneOf: - type: string - type: array items: type: object description: >- A content block. Supported types: `text`, `image` (base64 source, vision models only), `tool_use`, `tool_result` (text content, optional `is_error`). properties: type: type: string enum: - text - image - tool_use - tool_result text: type: string source: type: object description: >- For `image`: `{type: "base64", media_type, data}`. URLs and Files API images are not supported. id: type: string name: type: string input: type: object tool_use_id: type: string content: oneOf: - type: string - type: array items: type: object is_error: type: boolean example: - role: user content: Hello system: oneOf: - type: string - type: array items: type: object description: System prompt, as a string or text blocks. stream: type: boolean default: false description: >- Server-sent events in Anthropic order. Use it for long replies. temperature: type: number stop_sequences: type: array items: type: string description: >- Applied by the Grid. Tokens the node generated past the match are still billed. tools: type: array items: type: object properties: name: type: string description: type: string input_schema: type: object description: >- Your own tools with an `input_schema`. Server tools and Anthropic-defined tools are refused. tool_choice: type: object description: >- `{type: auto | any | tool | none}`. `disable_parallel_tool_use: true` is refused. thinking: type: object description: >- Accepted as a no-op for `adaptive`, `disabled`, `between_tools`. `enabled` with `budget_tokens` is refused. metadata: type: object description: Accepted, no effect. responses: '200': description: The message, or an SSE stream when `stream` is true. content: application/json: schema: type: object properties: id: type: string type: type: string example: message role: type: string example: assistant model: type: string content: type: array items: type: object description: >- A content block. Supported types: `text`, `image` (base64 source, vision models only), `tool_use`, `tool_result` (text content, optional `is_error`). properties: type: type: string enum: - text - image - tool_use - tool_result text: type: string source: type: object description: >- For `image`: `{type: "base64", media_type, data}`. URLs and Files API images are not supported. id: type: string name: type: string input: type: object tool_use_id: type: string content: oneOf: - type: string - type: array items: type: object is_error: type: boolean stop_reason: type: string enum: - end_turn - max_tokens - stop_sequence - tool_use - refusal stop_sequence: type: string nullable: true usage: type: object properties: input_tokens: type: integer output_tokens: type: integer cache_creation_input_tokens: type: integer example: 0 cache_read_input_tokens: type: integer example: 0 cost_usd: type: number description: 'Extra field: what this call was charged.' text/event-stream: schema: type: string description: >- Events: message_start, content_block_start, content_block_delta (text_delta, input_json_delta), content_block_stop, message_delta, message_stop, ping, error. '400': description: >- `invalid_request_error`: unsupported field or feature, or the prompt does not fit the model's context. content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '402': description: >- `billing_error`. Also carries the x402 fields (`x402Version`, `accepts`, `price_usd`) at the top level and a `WWW-Authenticate` header, so x402 clients can pay and retry. content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '404': description: '`not_found_error`: the model is not served right now.' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '429': description: '`rate_limit_error`.' content: application/json: schema: $ref: '#/components/schemas/AnthropicError' '504': description: >- `timeout_error`: a non-streaming reply ran past the sync window. The job continues and is billed; `job_id` is included and `x-should-retry: false` is set. Use `stream: true` for long replies. content: application/json: schema: $ref: '#/components/schemas/AnthropicError' components: schemas: AnthropicError: type: object description: >- Anthropic-shaped error. The Grid's own detail (for example `code`, `context_limit`, `job_id`) rides along inside `error`. properties: type: type: string example: error error: type: object properties: type: type: string enum: - invalid_request_error - authentication_error - billing_error - permission_error - not_found_error - rate_limit_error - timeout_error - api_error - overloaded_error message: type: string request_id: type: string ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.