Start with the models and coding agents developers ask for first: DeepSeek, Kimi, GLM, Codex, and Claude Code. One key, prepaid balance, pay per successful call.
Every model. Every tool. One invoice.
Build with Claude Code, Codex, OpenClaw, or any app. Flatkey runs search, browsers, enrichment, media generation, and actions through one balance—then bills only successful calls.
Use one Flatkey interface for leading AI models, social platforms, web data, crawlers, GTM intelligence, and more.







No provider credentials scattered across agents, repos, and environments.
Consistent schemas, error envelopes, request IDs, and usage records.
Control which agents can call which tools and how much they may spend.
Models and tools share one balance; failed Flatkey-side calls cost nothing.
One request, five upstream channel classes. When a channel degrades, the router reroutes automatically — and the SLA is a public document, not a sales promise.
When one upstream errors, the router recovers on the next-best official channel — you see one flat line.
National-lab models from 60% of list, stacking with the top-up bonus to 40%; flagships bill at list with the same bonus. One prepaid balance across every model.
claude-opus-4-8 · $/1M input tokens, after bonus
Every request hits the real lab API — no fp8 re-serves, no silent swaps. 300+ models probed against official fingerprints, on a public log.
Point Codex, Claude Code, OpenClaw, or any agent CLI at Flatkey’s SKILL.md. It learns how to discover and call 300+ official models and 1,000+ pay-per-call tools with one key.
$ codex "Set up Flatkey from https://flatkey.ai/SKILL.md" ✓ 300+ official models connected ✓ 1,000+ tools discovered ✓ one key · one balance
Tree-structured sub-keys with budgets and model allowlists, a per-request ledger API, invoices in 48h — on audited infrastructure.
Per-request ledger with input, output and cached tokens — exportable, API-accessible. Invoices in 48h (VAT fapiao supported), 3DS payments, sub-key caps and model allowlists for teams.
OpenAI, Anthropic, Google, DeepSeek, Alibaba, Zhipu, Moonshot, ByteDance… new models live within 24h of official release — always the real endpoints, never quantized re-serves.
Text-to-video and image-to-video from every major lab — metered per second on the same prepaid balance as your text models.
Integration, model choice, or billing — online support and usage consultation for everything on flatkey.
Whether you ship an agent today or route billions of tokens a month — one key, a signed SLA, and prices that drop as you grow.