Documentation
How it works
- Create a key in the portal — every account starts with $1 in free credit, no card required.
- Point your client at the gateway — it speaks the Anthropic and OpenAI wire formats your tools already use.
- Pick any model with the usual
modelfield — one key reaches the whole catalog at native per-token rates.
Three minutes end to end — the quickstart has copy-paste requests for both wire formats.
Connect your coding agent
Each agent has a dedicated page with the exact config, which models it reaches, and its known gotchas:
Claude Code
Claude and the open-weight daily drivers in Claude Code.
Codex
OpenAI Codex on the Responses wire.
Cursor
Open-weight, Claude, and GPT-5.6 as Cursor custom models.
Kilo Code
The full catalog from one kilo.json — CLI and VS Code extension.
ZCode
Z.ai's GLM-5.2 harness on your InferenceHub key.
Hermes
Open-weight chat models in the Hermes CLI.
Memmy
One memory layer across your agents, on your InferenceHub key.
Explore
API overview
Wire formats, base URLs, authentication, streaming.
Image generation
OpenAI Images API — gpt-image-2 and gpt-image-1.5.
Embeddings & rerank
Embedding and reranker models for RAG pipelines.
Models
Model ids, aliases, and how to list what your key reaches.
Auto routing
ih-auto and ih-auto-smart — a flat sheet, per-request routing, and honest escalation.
Model synthesis
ih-synthesis presets and the model_synthesis tool — a model panel answers, a synthesizer merges.
Billing & plans
Prepaid balance, subscription plans, free chat models, and the daily reward.
Desktop app
The open-source native client for the hosted chat.
Telegram bot
Chat with your models inside Telegram, billed to your own account.
Troubleshooting
Common HTTP errors and per-agent fixes.
Support
Discord, Telegram, email, and the status page.