PAYG / no subscriptions

Pay for tokens. Not promises.

Separate input, output, and cache rates. No seat fee, monthly minimum, or expiry on funded balance. Top up when you need capacity.

$5 minimumCrypto top-ups
No expiryUse it on your schedule
40% cost markupSimple sustainable margin
Real usagePer-request accounting
ModelExact API IDInput / 1MOutput / 1MAvg TPS / 24hCapabilities
GPT-6.2 AstraOpenAIgpt-6.2-astra
$0.0672$0.252Collecting
reasoningcodeflagship
GPT-6.2 SolOpenAIgpt-6.2-sol
$0.0672$0.252Collecting
reasoningcodegeneral
GPT-6.1 SolOpenAIgpt-6.1-sol
$0.0672$0.252Collecting
generalcode
GPT-6.1 TerraOpenAIgpt-6.1-terra
$0.0538$0.242Collecting
fastcode
GPT-6 AstraOpenAIgpt-6-astra
$0.202$0.756Collecting
reasoningflagship
GPT-6 LunaOpenAIgpt-6-luna
$0.0054$0.020250.3
fastcode
Claude Opus 5.5Anthropicclaude-opus-5-5
$0.202$0.756Collecting
reasoningflagship
Claude Sonnet 5.5Anthropicclaude-sonnet-5-5
$0.0672$0.252Collecting
reasoningcode
Claude Haiku 5.5Anthropicclaude-haiku-5-5
$0.0538$0.242Collecting
fastcode
Gemini 4 HydrogenGooglegemini-4-hydrogen
$0.210$1.050Collecting
reasoningmultimodal
DeepSeek V4.1 Flash 1017 UncensoredDeepSeekdeepseek-v4.1-flash-1017-uncensored
$0.104$0.312Collecting
fastuncensored
GLM 5.3 AbliteratedZhipu AIglm-5.3-abliterated
$0.728$2.421Collecting
reasoningabliterated
GLM 5.3 Flash AbliteratedZhipu AIglm-5.3-flash-abliterated
$0.218$0.910Collecting
fastabliterated
Billing details
How is a request calculated?

New input, cached input, cache writes, and output tokens are multiplied by their published per-million rates. Reasoning tokens count as output. Your usage log shows the exact tokens and charge for each request.

Why not match every competitor rate?

Some public competitor prices are below our upstream cost. We would rather keep a sustainable margin than quietly lose money, degrade routes, or freeze service. On many directly comparable models SafeAPI is substantially cheaper; on others you can choose the route that makes sense for you.

Do failed requests cost money?

Requests rejected before reaching the upstream are not charged. Once an upstream starts processing, its actual reported token usage can be billable even if a stream disconnects. Estimated or reconciled charges are labeled in your usage history.

How does caching affect my price?

SafeAPI passes through supported provider-side prompt caching. Cache reads and writes use their own rates. We do not promise cache hits or operate a shared semantic cache with your private prompts.

Start with $5