IgnitronDev Router — One API. Multiple AI Models.
IgnitronDev Router is an AI API router that gives developers one endpoint and one key for multiple large language models, with unified billing and usage tracking.
IgnitronDev Router is an AI API router: one endpoint, one key, multiple LLMs. OpenAI- and Anthropic-compatible, with unified billing and usage tracking.
Models routable today
- Claude Opus 4.8 (Anthropic)
- Claude Opus 5 (Anthropic)
- GPT-5.6 Sol (OpenAI)
Models from Google, DeepSeek, Meta, Mistral are listed in the catalog as coming soon and are not yet routable.
Endpoints
- OpenAI-compatible:
https://agent.ignitrondev.space/v1/chat/completions - Anthropic-compatible:
https://agent.ignitrondev.space/v1/messages
Access and pricing
IgnitronDev Router is in a closed beta: signup requires a valid invite code. New accounts start with $15 of promotional API credit valid for 14 days, no credit card required. Usage is then billed per request at provider token rates.
Frequently asked questions
What is IgnitronDev Router?
IgnitronDev Router is an AI API router that gives developers one endpoint and one key for multiple large language models. You send a request to one base URL, IgnitronDev Router authenticates it, routes it to the right upstream model, and records the tokens and cost against your wallet.
Which AI models can I use through IgnitronDev Router?
Claude Opus 4.8 and Claude Opus 5 from Anthropic and GPT-5.6 Sol from OpenAI are routable today, across both API dialects. Models from Google, DeepSeek, Meta and Mistral are listed in the catalog as coming soon and are not yet routable — IgnitronDev Router marks them clearly rather than accepting requests it cannot serve.
Is IgnitronDev Router compatible with the OpenAI SDK?
Yes. IgnitronDev Router exposes an OpenAI-compatible endpoint at https://agent.ignitrondev.space/v1/chat/completions and an Anthropic-compatible endpoint at https://agent.ignitrondev.space/v1/messages. Point an existing SDK at the base URL, swap in your IgnitronDev Router key, and no other code changes are needed. Streaming is supported on both.
How is IgnitronDev Router different from calling provider APIs directly?
Calling providers directly means one account, one key and one bill per provider, and provider keys inside your codebase. With IgnitronDev Router you hold a single key, switch models by changing one parameter, and see spend from every provider in one wallet. Upstream provider credentials stay server-side and are never exposed to your application.
How much does IgnitronDev Router cost?
Usage-based: you pay per request at provider token rates, drawn from your wallet. New GitHub accounts start with $15 of promotional credit valid for 14 days; a valid referral adds another $15. Promotional credit is spent before paid balance; paid balance does not expire.
How do I create an IgnitronDev Router account?
Use the Sign up with GitHub button. GitHub is the only account and sign-in method; a genuinely new account receives $15 of promotional API credit valid for 14 days, or $30 when joining through a valid referral link.
Does IgnitronDev Router store my prompts?
No. IgnitronDev Router records request metadata only — model, token counts, cost, latency and HTTP status — so the dashboard can show usage. Prompt and completion content is not written to its logs or database.
What happens when promotional credit expires?
Unused promotional credit stops applying at its expiry date and cannot be reinstated, transferred or withdrawn — it is credit against API usage, not cash. Requests then draw on paid balance, and a request is refused if neither balance can cover it.
Create an account · Sign in · support@ignitrondev.space
