Chat completions with the exact request and response shape of the OpenAI API
Chat completions with the exact request and response shape of the OpenAI API: point your existing client at this URL and it works, no code change. One flat price per call whatever the size of the prompt or the answer — no token metering, no API key, no account, no rate limit. Automatic failover across several large models, so a model being down is not your problem. You are only charged if the completion is delivered.
Answeringour last check, 2026-10-18
1 of 1checks answered this week
27 msmedian answer time
$0.005listed price per call
$0.005price it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
GET https://flat-rate-llm.kikoribera03.workers.dev/v1/chat/completions
| Category | Code and developer |
|---|---|
| Provider host | flat-rate-llm.kikoribera03.workers.dev |
| Networks | eip155:137, eip155:42161, eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 2 from 2 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-18 | valid payment request | 402 | $0.005 | 27 ms |
Example input (from the provider)
{
"method": "GET",
"queryParams": {
"messages": "[{\"role\":\"user\",\"content\":\"Summarise in one line what the x402 protocol is.\"}]"
},
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"method": {
"enum": [
"GET"
],
"type": "string"
},
"queryParams": {
"properties": {
"max_tokens": {
"description": "Output token cap, up to 4000. Does not change the price.",
"type": "number"
},
"messages": {
"description": "The conversation, as in the OpenAI API: [{\"role\":\"system|user|assistant\",\"content\":\"...\"}]. In a POST, send it as a real JSON array, exactly as an OpenAI client does; in a GET, pass that same JSON as text in the query string. Both are accepted.",
"type": "string"
},
"model": {
"description": "Ignored on purpose: the service picks the model and fails over between several. Accepted so an OpenAI client can send it unchanged.",
"type": "string"
},
"prompt": {
"description": "Shortcut for a single user message, if you do not want to build the array.",
"type": "string"
},
"temperature": {
"description": "Passed through to the model when given.",
"type": "number"
}
},
"required": [],
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}