Kimi K3, Chat, Cached Input
Overview
Kimi K3, Chat, Cached Input is a chat-generation model served via Other. Access it with the same Bearer token and OpenAI-compatible request shape as the other 287 models in the catalog — no provider-specific SDK required. Priced at $0.3360 per million tokens, billed per use from your credit balance.
Use via API
curl https://aimarcusimage.eu/api/v1/chat/completions \
-H "Authorization: Bearer sk-aig-..." \
-H "Content-Type: application/json" \
-d '{
"model": "Kimi K3",
"messages": [
{
"role": "user",
"content": "Hello from AI Generate"
}
]
}'
Async jobs (video / image / music) return a taskId. Poll /api/v1/jobs/recordInfo?taskId=... or use a webhook to get the result URLs.
Prompt examples
Pricing compare
| Provider | Price per million tokens | Notes |
|---|---|---|
| AI Generate | $0.3360 | This site, pay-as-you-go from $10, no subscription |
| Direct from Other | varies | Requires separate account and higher minimum commitment |
Related models
Gemini 3.8 Flash, chat, input
gpt-6-astra, chat, Cache Writes
DeepSeek V4.1 Flash, Chat, Input
Gemini 3.8 Flash, chat, output
Kimi K3, Chat, Output
DeepSeek V4.1 Flash, Chat, Output
FAQ
How much does Kimi K3, Chat, Cached Input cost?+
$0.3360 per million tokens. You pay from your credit balance — no monthly subscription, no minimum commitment. The Starter plan is $10 → 1,430 credits, top up only when you need.
Is Kimi K3, Chat, Cached Input a chat model?+
Yes — Kimi K3, Chat, Cached Input is a chat-generation model from Other, served through the AI Generate gateway.
How do I call Kimi K3, Chat, Cached Input from my code?+
Use a standard HTTPS POST with a Bearer token to our /api/v1/ endpoint. The request shape matches the OpenAI-compatible convention — no provider-specific SDK needed. See the "Use via API" section above for a working curl example.
Can I use Kimi K3, Chat, Cached Input in production?+
Yes. The endpoint is rate-limited to 20 requests per 10 seconds per API key, retries are idempotent via taskId, and async results are delivered via polling or webhook. Set a daily spend cap in dashboard settings to protect against runaway usage.
What is the markup compared to the upstream provider?+
We route through a mix of direct provider integrations (OpenAI, Anthropic) and wholesale aggregators (kie.ai, OpenRouter) — typically 20-40% above raw provider cost. Volume tiers at $50 / $200 / $1000 / $5000 monthly spend reduce the markup to as low as 10%.
Ready to try Kimi K3, Chat, Cached Input?
Sign up in 30 seconds. Top up $10 (1,430 credits) — enough for dozens of generations.