C
Surf Inference
Preview responses and set spending limits for this service through use.mpp.land
Free budget controls, response samples, and reliability routing.
Compliance Checks
All paid ops declare 402 response
MUST
10pt
All x-payment-info valid
MUST
10pt
Challenge has Cache-Control: no-store
MUST
5pt
Challenge digest on POST
SHOULD
3pt
Challenge has expires
SHOULD
3pt
Challenge has Problem Details
SHOULD
2pt
Challenge has required params
MUST
5pt
Challenge has WWW-Authenticate
MUST
5pt
Challenge returns 402
MUST
10pt
Correct Content-Type
MUST
5pt
Has Cache-Control on discovery
SHOULD
5pt
Has input schemas
SHOULD
5pt
Has llms.txt
SHOULD
5pt
Has /openapi.json at root
MUST
10pt
Has required top-level fields
MUST
10pt
Served over HTTPS
MUST
10pt
Uses standard categories
SHOULD
2pt
2 issues
- 402 response missing Cache-Control: no-store
- POST endpoint challenge missing digest parameter (SHOULD per spec)
Paid Operations (1)
POST /v1/chat/completions dynamic
Chat completion
OpenAI-compatible chat completion endpoint with x402 or MPP payment. Supports streaming via SSE. Flat-priced models: qwen/qwen-2.5-7b-instruct ($0.001). Dynamic-priced models (scales with prompt size and max_tokens): moonshotai/kimi-k2.5, minimax/minimax-m2.7, z-ai/glm-5, x-ai/grok-4.1-fast, x-ai/grok-4.20-beta, x-ai/grok-4.20-multi-agent-beta, anthropic/claude-sonnet-4.5, anthropic/claude-sonnet-4.6, anthropic/claude-opus-4.5, anthropic/claude-opus-4.6. Search-enabled variants (include live X/Twitter + web search via xAI native tools): x-ai/grok-4.1-fast:online, x-ai/grok-4.20-beta:online, x-ai/grok-4.20-multi-agent-beta:online. Default max_tokens: 4096 when omitted.
- Amount
- dynamic
- Currency
- -
- Method
- x402, mpp
- Intent
- -
- 402 Declared
- Yes
Non-standard x-payment-info fields:
pricingMode: quote protocols: [x402 mpp]
Input Schema
{
"$ref": "#/components/schemas/ChatCompletionBody"
}
Response Schema (200)
{
"$ref": "#/components/schemas/ChatCompletionResponse"
}
Payment Methods
- Methods
- tempo (from challenge)
- Intents
- charge, session (from challenge)
- Currencies (discovery)
- -
- Currency (challenge)
- USDC.e on Tempo (Tempo)
- Multiple Challenges
- Yes
Recipients
- 0x2BB201f1bb056eb738718BD7A3ad1BEF24b883bb
Per-endpoint breakdown
- POST /v1/chat/completions
- 0x2BB201f1bb056eb738718BD7A3ad1BEF24b883bb
Security
- TLS Version
- TLSv1.3
- Challenge ID Unique
- Yes
- Challenge ID Length
- 43
- Digest Binding
- -
Uptime
- Discovery
- Reachable (146ms)
- Challenge
- Reachable (87ms)
- Last Checked
Schema Completeness
- Paid Operations
- 1
- With Input Schema
- 1
- With Description
- 1
Documentation
- Homepage
- -
- API Reference
- -
- llms.txt
- -
Discovery
- OpenAPI URL
- https://inference.surf.cascade.fyi/openapi.json
- OpenAPI Version
- 3.1.0
- Service Version
- 1.0.0
- Document Size
- 4795 bytes
- Document Hash
- f8dbce3af58e02d29afab8fab8af2114514193b58139668d8134ce171f6f554d
Version History (2 snapshots)
Scan snapshots
| Date | Grade | Score | Response | Status |
|---|---|---|---|---|
| 2026-04-06 | C | 69% | 213ms | Up |
| 2026-04-07 | C | 69% | 481ms | Up |