Live 2 frontier models ready on one endpoint

One API for
frontier models.

OpenGray routes your requests to Claude Fable 5 and GPT-5.6 Sol through a single OpenAI-compatible endpoint. Buy credits, generate a key, ship. No subscription, no seat licences, no minimum spend.

Credits never expire · Billed per token, to six decimal places · 100 credits = US$1.00

curl https://open-gray.com/api/v1/chat/completions \
  -H "Authorization: Bearer sk-og-v1-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-fable-5",
    "messages": [
      { "role": "user", "content": "Summarise our Q3 revenue drivers." }
    ]
  }'
OpenAI-compatible - point any SDK at the OpenGray base URL.
2
Frontier models
1.05M
Max context
100
Credits per US$1
Per token
Billing granularity
OpenAI
Wire compatible

Catalogue

Two models, chosen deliberately

We carry the strongest reasoning model from each frontier lab instead of a directory of hundreds. Prices below are what you pay, in credits per million tokens.

All model details

Claude Fable 5

Anthropic · claude-fable-5
Best for agents

Mythos-class reasoning for autonomous knowledge work.

1M context 128K max output Extended reasoning Tool calling Structured outputs
Input
1,000 cr / M tokens
Output
5,000 cr / M tokens

GPT-5.6 Sol

OpenAI · gpt-5.6-sol
Best value

Flagship GPT-5.6 model for coding and agentic work.

1.05M context 128K max output Adjustable reasoning Tool calling Structured outputs
Input
500 cr / M tokens
Output
3,000 cr / M tokens

Platform

Built for teams that ship

Everything you need to run production traffic, and nothing you don't.

Drop-in compatible

Change two lines: the base URL and the key. Any OpenAI SDK, LangChain, or plain HTTP client works unchanged, streaming included.

Honest per-token billing

Every request is metered against the generation's real token usage and settled to six decimals. No rounding up to whole cents.

Keys with spend limits

Issue a key per environment, cap it in credits, and revoke it instantly. Keys are stored as SHA-256 hashes and shown once.

Usage you can audit

Per-request logs with tokens, latency, model and credits charged. Export-ready tables for finance and engineering.

Prompt caching passthrough

Cached input tokens are billed at the cache rate, so repeat context in long agent loops stays inexpensive.

Sensible defaults

TLS everywhere, hashed credentials, row-level-secured storage and rate-limited authentication out of the box.

How it works

Three steps to your first token

  1. Create an account. Email and password only. A default API key is generated for you immediately.
  2. Add credits. Top up any amount from $5.00 on Whop. Every US$1 becomes 100 credits, applied the moment payment clears.
  3. Send a request. Point your SDK at https://open-gray.com/api/v1 and call any model in the catalogue.
Credits
From $5
500+ credits ยท choose your amount
  • One-time purchase, no subscription
  • Credits never expire
  • All models included
Create account

Start with a few dollars, not a contract

Credits are pay-as-you-go and never expire. If OpenGray isn't a fit, stop sending requests — there is nothing to cancel.