Connect once. Roteo any model.
Claude, GPT, image and video models through one drop-in endpoint, at up to 93% below list price. Pay per call, no subscription.
Claude, GPT, image and video models through one drop-in endpoint, at up to 93% below list price. Keep the tools you already use and just swap the base URL. Pay per call, no subscription.
Everything you need to route models.
A single base URL fronts every provider, with billing, failover and controls handled for you.
One endpoint, every model
Route Claude, GPT and more through a single base URL. Swap models without touching your integration.
Pay per call
You pay for the requests you make, nothing else. No subscriptions, no seats, no minimums.
Automatic failover
A provider stumbles, the request reroutes instantly. Never a dropped call.
Full metering
Every token tracked and attributed, down to the individual request.
Models on tap
Claude, GPT and more, ready to call. New models land as they ship.
Image and video generation
Generate and edit images, or turn a prompt into video, through the same endpoint and key. Text, pixels and motion, one integration.
Open-weight models
Coming soonRun abliterated open-weight models through the same endpoint. Fewer refusals, more control.
Your wallet. Every model. Per request.
No account funded with us, no prepaid credits. You hold your own balance and each call settles onchain as you make it.
Get your wallet
Sign in and get a self-custodied wallet that only you control.
Fund it with stablecoins
Top up a supported stablecoin to fund your balance on any chain.
Authorized for you
We set the per-call billing up for you, capped by your balance.
Pay as you call
Every request settles onchain over x402 the moment you call.
Pay per call, every model.
Final price per million tokens, settled onchain in stablecoins. There are no card processors or subscription margins baked in, so you pay the metered rate and nothing on top.
Claude models
claude-fable-5-1Input
$1.900 /M
Output
$9.300 /M
Cached
$0.080 /M
claude-fable-5Input
$1.850 /M
Output
$9.250 /M
Cached
$0.200 /M
claude-opus-5-5Input
$0.650 /M
Output
$3.100 /M
Cached
$0.050 /M
GPT models
gpt-6-astraInput
$0.700 /M
Output
$3.350 /M
Cached
$0.080 /M
gpt-6.1-solInput
$0.150 /M
Output
$0.700 /M
Cached
$0.010 /M
gpt-6-lunaInput
$0.015 /M
Output
$0.050 /M
Cached
$0.005 /M
Third-party models
deepseek-v4-flash-0731Input
$0.506 /M
Output
$1.518 /M
Cached
$0.032 /M
qwen3.8-maxInput
$2.300 /M
Output
$6.900 /M
Cached
$0.287 /M
kimi-k3Input
$3.450 /M
Output
$17.250 /M
Cached
$0.345 /M
glm-5.3Input
$1.610 /M
Output
$5.060 /M
Cached
$0.299 /M
glm-5.3-flashInput
$0.172 /M
Output
$0.575 /M
Cached
$0.035 /M
Prices are per 1,000,000 tokens. Prompt-cache writes are billed at 2x the input rate (1-hour cache).
Image generation
Generate and edit images through the same endpoint and key. Final price per image, settled onchain, with nothing added on top.
Image models
1K
$0.114 /img
2K
$0.154 /img
4K
$0.204 /img
1K
$0.068 /img
2K
$0.135 /img
4K
$0.135 /img
1K
$0.066 /img
2K
$0.086 /img
4K
$0.128 /img
Prices are per generated image. You only pay for images successfully delivered.
Video generation
Generate video from text or an image through the same endpoint and key. Final price per clip by duration, settled onchain, with nothing added on top.
Video models
5s
$1.057+ /clip
16s
$3.362+ /clip
30s
$6.296+ /clip
4s
$0.360 /clip
8s
$0.720 /clip
12s
$1.080 /clip
5s
$0.150+ /clip
8s
$0.240+ /clip
Prices are per generated clip. Most models charge by duration and resolution, so a longer or sharper clip costs more. You only pay for clips successfully delivered.
Questions, answered.
Route your first request today.
One key, every model, billed by the request. No subscriptions, no setup.