LLM inference API
LLM inference API: OpenAI-compatible chat completions for 100+ AI models (DeepSeek, GPT, Claude, Gemini, Grok, GLM, Qwen, Kimi, Llama, Mistral). Suited for AI agents that need on-demand text generation, coding or tool calling paid per request in USDC on Base with x402: no account, no API key. Model in body.model (GET /v1/models); streaming supported. Exact price in the 402 quote; automatic refund if the model fails.
Answeringour last check, 2026-10-18
1 of 1checks answered this week
774 msmedian answer time
$0.0014listed price per call
$0.0014price 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
POST https://agent402-arb.rosariovitale0096.workers.dev/v1/chat/completions
| Category | Market data |
|---|---|
| Provider host | agent402-arb.rosariovitale0096.workers.dev |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 8 from 3 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-18 | valid payment request | 402 | $0.0014 | 774 ms |
Example input (from the provider)
{
"body": {
"max_tokens": 12,
"messages": [
{
"content": "Reply with OK",
"role": "user"
}
],
"model": "deepseek/deepseek-chat",
"stream": false
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"max_tokens": {
"description": "Optional, default 4096",
"maximum": 16384,
"minimum": 1,
"type": "integer"
},
"messages": {
"items": {
"properties": {
"content": {
"type": [
"string",
"array",
"null"
]
},
"role": {
"enum": [
"system",
"user",
"assistant",
"tool",
"developer"
],
"type": "string"
}
},
"required": [
"role"
],
"type": "object"
},
"minItems": 1,
"type": "array"
},
"model": {
"description": "Choose any current model; GET /v1/models for the live catalog.",
"examples": [
"anthropic/claude-fable-5",
"anthropic/claude-fable-5.1",
"anthropic/claude-haiku-4.5",
"anthropic/claude-haiku-5.5",
"anthropic/claude-opus-4.5",
"anthropic/claude-opus-4.6",
"anthropic/claude-opus-4.7",
"anthropic/claude-opus-4.8",
"anthropic/claude-opus-4.8-fast",
"anthropic/claude-opus-5",
"anthropic/claude-opus-5-fast",
"anthropic/claude-opus-5.5",
"anthropic/claude-opus-5.5-fast",
"anthropic/claude-sonnet-4.5",
"anthropic/claude-sonnet-4.6",
"anthropic/claude-sonnet-5",
"anthropic/claude-sonnet-5.5",
"deepseek/deepseek-chat",
"deepseek/deepseek-reasoner",
"deepseek/deepseek-v3.2",
"deepseek/deepseek-v4-flash-0731",
"deepseek/deepseek-v4-flash-0731-fast",
"deepseek/deepseek-v4-flash-vision-exp",
"deepseek/deepseek-v4-pro",
"deepseek/deepseek-v4-pro-0813",
"deepseek/deepseek-v4.1-flash",
"google/gemini-2.5-flash",
"google/gemini-2.5-flash-lite",
"google/gemini-2.5-pro",
"google/gemini-3-flash-preview",
"google/gemini-3.1-flash-lite",
"openai/gpt-4.1",
"openai/gpt-4.1-mini",
"openai/gpt-4.1-nano",
"openai/gpt-4o",
"openai/gpt-4o-mini",
"openai/gpt-5-mini",
"openai/gpt-5.1",
"openai/gpt-5.2",
"openai/gpt-5.2-pro",
"openai/gpt-5.3-codex",
"openai/gpt-5.4",
"openai/gpt-5.4-mini",
"openai/gpt-5.4-nano",
"openai/gpt-5.4-pro",
"openai/gpt-5.5",
"openai/gpt-5.5-pro",
"openai/gpt-5.6-luna",
"openai/gpt-5.6-luna-pro",
"openai/gpt-5.6-sol",
"openai/gpt-5.6-sol-pro",
"openai/gpt-5.6-terra",
"openai/gpt-5.6-terra-pro",
"openai/gpt-6-astra",
"openai/gpt-6-astra-pro",
"openai/gpt-6-luna",
"openai/gpt-6-sol",
"openai/gpt-6.1-sol",
"openai/gpt-6.1-sol-ultrafast",
"openai/gpt-oss-120b"
],
"type": "string"
},
"response_format": {
"type": "object"
},
"stream": {
"description": "true: server-sent events after payment",
"type": "boolean"
},
"temperature": {
"maximum": 2,
"minimum": 0,
"type": "number"
},
"tools": {
"type": "array"
}
},
"required": [
"model",
"messages"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"headers": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"method": {
"enum": [
"POST",
"PUT",
"PATCH"
],
"type": "string"
},
"queryParams": {
"additionalProperties": {
"type": "string"
},
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"properties": {
"choices": {
"items": {
"required": [
"index",
"message",
"finish_reason"
],
"type": "object"
},
"type": "array"
},
"id": {
"type": "string"
},
"model": {
"type": "string"
},
"object": {
"const": "chat.completion"
},
"usage": {
"type": "object"
}
},
"required": [