Hunt Townh402
Catalog
AIPOSTlive

LLM chat completions

Call OpenAI-compatible chat completion models through a request-priced paid API.

$0.00-$5.00
per call
Success
100%
p50 latency
2.36s
p95 latency
4.08s
Calls (30d)
4

Provider contract

Call path
/routes/blockrun/ai/chat-completions
Method
POST
Selected provider
blockrundefault
Provider price
Dynamic $0.00-$5.00; quote required
Settlement
Base USDC · x402 · 5% h402 fee

Quickstart

Both commands call the selected provider directly.

cURL
curl -X POST '/routes/blockrun/ai/chat-completions' \
  -H 'content-type: application/json' \
  -d '{"model":"openai/gpt-5.5","messages":[{"role":"user","content":"Summarize the benefits of API observability in one sentence."}]}'
CLI
h402 call 'ai/chat-completions' --provider 'blockrun' --method POST --json '{"model":"openai/gpt-5.5","messages":[{"role":"user","content":"Summarize the benefits of API observability in one sentence."}]}'

Parameters & live test

pays real USDC

Fill the request fields, quote the exact per-call total, then choose x402 or eligible bonus credit explicitly before sending. Only the selected provider's listed parameters are accepted.

modelstringrequired

OpenAI-compatible, provider-prefixed model id (vendor/model), e.g. openai/gpt-5.5. Use Load live values for the full BlockRun model list.

e.g.
messagesarrayrequired

OpenAI-compatible chat messages.

max_tokensnumberoptional≥ 1

Optional cap on completion tokens (e.g. 256-1024). No fixed maximum: bounded by the selected model's own context window.

e.g.
POST/routes/blockrun/ai/chat-completions
Request body
{
  "model": "openai/gpt-5.5",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the benefits of API observability in one sentence."
    }
  ]
}

ResponseExample response
{
  "data": {
    "id": "chatcmpl-E4TUpzbanFFNRY3CXz5JLLJNVOiKx",
    "object": "chat.completion",
    "created": 1784735403,
    "model": "openai/gpt-5.5",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "API observability helps teams monitor performance, detect and troubleshoot issues faster, improve reliability, understand usage patterns, and deliver better user experiences."
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 19,
      "completion_tokens": 31,
      "total_tokens": 50,
      "prompt_tokens_details": {
        "audio_tokens": 0,
        "cached_tokens": 0
      },
      "completion_tokens_details": {
        "accepted_prediction_tokens": 0,
        "audio_tokens": 0,
        "reasoning_tokens": 0,
        "rejected_prediction_tokens": 0
      }
    }
  },
  "h402": {
    "routeId": "ai/chat-completions",
    "provider": "blockrun",
    "selectedCandidateId": "ai/chat-completions/blockrun",
    "routing": "manual",
    "paidBy": "x402-exact"
  }
}

Providers

Choose a provider for this task. The catalog recommends the current default from quality, reliability, and price; your selected provider stays pinned. Listed prices are provider prices; settlement adds a 5% h402 fee.

blockrun
x402
100
Success
100%
p50
2.36s
Calls
4
100%
Dynamic $0.00-$5.00; quote required$0.0015/call
Last successful call: 10h ago· Aggregated by h402 — not the source provider