Documentation

https://ohhmyagent.com/v1/messages          # Anthropic Messages API
https://ohhmyagent.com/v1/chat/completions   # OpenAI Chat Completions
https://ohhmyagent.com/v1/responses          # OpenAI Responses API (Codex)
https://ohhmyagent.com/v1/models             # list available models

ohh/claude-fable-5 # Claude Fable 5 (Fable Only wallet)
ohh/claude-opus-5         # Claude Opus 5  (GPT + Opus wallet)
ohh/claude-opus-4.8       # Claude Opus 4.8 (GPT + Opus wallet)
ohh/gpt-5.6        # GPT 5.6 auto-burst  (Sol -> Terra -> Luna)
ohh/gpt-5.6-sol    # pin GPT to the Sol deployment
ohh/gpt-5.6-terra  # pin GPT to the Terra deployment
ohh/gpt-5.6-luna   # pin GPT to the Luna deployment

# Anthropic style
x-api-key: sk-mvx-your-key
anthropic-version: 2023-06-01

# OpenAI / Bearer style
Authorization: Bearer sk-mvx-your-key

{
  "id": "msg_01…",
  "type": "message",
  "role": "assistant",
  "model": "ohh/claude-opus-5",
  "content": [{ "type": "text", "text": "Hello!" }],
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 12, "output_tokens": 6 }
}

curl -N https://ohhmyagent.com/v1/messages \
  -H "x-api-key: sk-mvx-your-key" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"ohh/claude-opus-5","max_tokens":256,"stream":true,
       "messages":[{"role":"user","content":"Stream a haiku"}]}'

curl https://ohhmyagent.com/v1/responses \
  -H "authorization: Bearer sk-mvx-your-key" \
  -H "content-type: application/json" \
  -d '{"model":"ohh/gpt-5.6",
       "input":"Write a haiku about the sea",
       "reasoning":{"effort":"medium"}}'

{
  "id": "resp_…",
  "object": "response",
  "status": "completed",
  "model": "ohh/gpt-5.6",
  "output": [
    { "type": "message", "role": "assistant",
      "content": [{ "type": "output_text", "text": "Waves…" }] }
  ],
  "output_text": "Waves…",
  "usage": { "input_tokens": 9, "output_tokens": 17, "total_tokens": 26 }
}

event: response.created
event: response.in_progress
event: response.output_item.added
event: response.content_part.added
event: response.output_text.delta      # ← repeated, the tokens
event: response.output_text.done
event: response.content_part.done
event: response.output_item.done
event: response.completed              # ← final, carries usage

{
  "model": "ohh/claude-opus-5",
  "max_tokens": 1024,
  "tools": [{
    "name": "get_weather",
    "description": "Get current weather for a city",
    "input_schema": {
      "type": "object",
      "properties": { "city": { "type": "string" } },
      "required": ["city"]
    }
  }],
  "messages": [{ "role": "user", "content": "Weather in Jakarta?" }]
}

{
  "model": "ohh/claude-opus-5",
  "max_tokens": 512,
  "messages": [{ "role": "user", "content": [
    { "type": "image", "source": {
      "type": "base64", "media_type": "image/png", "data": "<BASE64>" } },
    { "type": "text", "text": "What is in this image?" }
  ]}]
}

{ "model":"ohh/claude-opus-5", "max_tokens":1024,
  "output_config": { "effort": "max" },
  "messages":[{"role":"user","content":"Prove there are infinitely many primes."}] }

Scoped billing. Fable uses only Fable lots. GPT uses GPT Only lots first, then eligible GPT + Opus lots. Opus uses only GPT + Opus lots. Wallets never cross-spend outside these rules.

Rate limits. 50 requests/minute per account (all keys share it) + 200 req/min per IP. Authenticated request body max 16 MiB. ChatRateLimited: Rate limit exceeded means your request rate exceeded the RPM controlled by our service; it is not an upstream incident.

Retries. For 429, the service honors Retry-After, waits with jitter, and retries automatically for up to 95 seconds. Transient 502/503/529 use exponential backoff.

Expiry. Token packs last 30 days as independent lots, consumed nearest-expiry first. Unlimited stacks an access window instead of tokens.

Which prefix — ohh/ or oma/?
Use ohh/. Bare canonical IDs such as claude-opus-5 / gpt-5.6 also resolve. Legacy shortened Opus IDs remain compatible, but are no longer advertised. There is no oma/.

Is GPT 5.6 OpenAI-only?
No — it works on both endpoints; we translate transparently. Pick the endpoint your SDK expects.

One key for all models?
One key can address every model ID, but the request is authorized and billed only from a wallet eligible for that model. Fable, GPT Only, and GPT + Opus balances remain separate.

Sol / Terra / Luna?
Three GPT 5.6 routes, same flat rate. ohh/gpt-5.6 auto-bursts; pin with -sol/-terra/-luna only if you want a fixed route.

Is my content stored?
No. We store only usage metadata (token counts, time, model). Conversation content is forwarded and not retained.

401 — check the key is correct & active; rotate on dashboard.

404 — wrong base URL. Claude Code = root (no /v1); SDKs = /v1. Never /v1/v1.

402 — top up your token wallet.

429 / ChatRateLimited — the request rate exceeded the service RPM limit, not an upstream issue. The service automatically waits and retries for up to 95 seconds. If it still appears, reduce concurrency, queue requests, and avoid parallel bursts.

529 — upstream busy; auto-retried — try again shortly.

wrong domain — always use ohhmyagent.com.