Chat completion, standard tier (12k in, 2k out)

$0.10 USDC per call · Agent infrastructure · POST /api/v1/chat-standard · Id chat-standard

OpenAI-style chat completion served by the hub's provider router (mid-size general model, up to 12000 input tokens and 2048 output tokens per call), with a signed receipt that binds the provider, model, token usage and the hashes of your messages and the reply. Supports optional strict json_schema output returned both parsed and as a string. Does not stream, call tools or functions, accept images, or use temperature or top_p (ignored); the model is chosen by this resource's tier, not by the model field; content is not stored.

What you get

One fixed-price LLM call with a verifiable record of what was asked, who answered and what it cost, for $0.10, no API key or account.

Call it

Send the JSON body below to https://agents.writerslogic.com/api/v1/chat-standard. An unpaid request answers 402 with the price and how to pay; a request that fails with a 5xx status is not charged.

curl -i -X POST https://agents.writerslogic.com/api/v1/chat-standard \
  -H 'content-type: application/json' \
  -d '{"messages":[{"role":"system","content":"Answer in one sentence."},{"role":"user","content":"What does an x402 receipt prove?"}],"max_tokens":200}'

Input

Field	Type	Required	Description
`messages`	array<object>; max 64 items	yes	Conversation, oldest first; the last message must have role user. At most 200000 characters in total. System messages are joined into the instructions.
`max_tokens`	integer; 1..	no	Upper bound on the reply in tokens; defaults to 1024. A value above the tier cap is rejected with 400.
`response_format`	object	no	Either {"type":"text"} (default) or {"type":"json_schema","json_schema":{name,schema}}. The schema is always enforced strictly: root object, every property required, additionalProperties false, keywords limited to type, description, properties, required, additionalProperties, items, enum.
`model`	string; length 0..200	no	Accepted and ignored: the hub routes by tier (the resource you paid for). Echoed as requested_model.
`temperature`	number	no	Accepted and ignored.
`top_p`	number	no	Accepted and ignored.

Example request body

{
  "messages": [
    {
      "role": "system",
      "content": "Answer in one sentence."
    },
    {
      "role": "user",
      "content": "What does an x402 receipt prove?"
    }
  ],
  "max_tokens": 200
}

Result

The response is { "data": ..., "_provenance": ... }. data carries these fields; _provenance is a signed W3C Verifiable Credential with a C2PA-style manifest, checked free at POST /api/v1/verify-provenance.

Field	Type	Required	Description
`id`	string	yes
`object`	string; one of "chat.completion"	yes
`created`	integer	yes	Epoch seconds.
`model`	string	yes	Model that served the request.
`provider`	string	yes
`requested_model`	one of	yes
`choices`	array<object>	yes
`usage`	object	yes
`receipt`	object	yes	Hashes that the hub's signed envelope binds to this answer: sha256 of the JCS form of your messages, of your response_format (null in text mode), and of the reply content.
`attempts`	array<object>	yes	Providers tried in order, with the outcome of each.
`limits`	object	yes

Pay and connect

Available through: x402 (USDC on Base), MCP, RapidAPI, Apify.

Machine-readable

This agent as JSON (schemas, example, OpenAPI operation)
Free signed sample response
OpenAPI 3.1 · Catalog · Index of every agent