Loading...
One model. One API. Pay only for the tokens you use. No subscriptions, no hidden fees, no limits.
Our prompt caching system automatically detects when you send similar prompts and reuses the cached result, saving you money on repeated requests. You pay the same price, but we pay $0 for cached responses.
When you send a prompt that matches a previously cached request, the system returns the stored response instantly without reprocessing. The cache key is based on the full prompt content, model, and parameters.
From your perspective, nothing changes. You get the same high-quality response at the same price. The only difference is faster response times and lower latency for cached prompts.
For us, cached responses cost $0 to serve. This means our margin increases on every cache hit. For you, it means faster responses and a more efficient system. Win-win.
# First request — full processing
curl -X POST https://api.list-cloud.com/v1/chat/completions \
-d '{"model":"list-sclak-v1","messages":[{"role":"user","content":"Summarize this document"}]}'
# Result: cache_miss = true, full processing
# Second request — same prompt, cached
curl -X POST https://api.list-cloud.com/v1/chat/completions \
-d '{"model":"list-sclak-v1","messages":[{"role":"user","content":"Summarize this document"}]}'
# Result: cache_hit = true, instant response, same priceA single model with all the tools to build, deploy, and scale.
Process entire codebases, books, and massive documents in a single request.
Read documents, analyze charts, understand UI screens, and answer visual questions.
Extract text from screenshots, scanned PDFs, receipts, invoices, and tables.
Interpret trends, values, and data from bar charts, line graphs, and pie charts.
No subscriptions, no commitments. Buy credit packs and use when you need.
Credits never expire. Use them at your own pace, for any project.
$0.50/M input tokens, $1.00/M output. No hidden fees.
Real-time dashboard with token usage, cost tracking, and spending insights.
Write, debug, and refactor code across 50+ languages with full context.
Multi-step logic, code generation, and complex problem solving in one call.
Enterprise-grade infrastructure with automatic failover and redundancy.
End-to-end encryption, SOC2 compliant, your data stays yours.
20M context, vision, code, reasoning — all in one model.
curl https://api.list-cloud.com/v1/chat/completions \
-H "Authorization: Bearer lc-sk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "list-sclak-v1",
"messages": [
{
"role": "user",
"content": "Analyze this chart"
}
],
"max_tokens": 4096
}'Transparent pricing, no subscription.
| Provider | Model | Input / 1M | Output / 1M | Context | Vision | Plan |
|---|---|---|---|---|---|---|
| List Cloud | List-Sclak-V1 | $0.50 | $1.00 | 20M | Yes | No subscription |
| OpenAI | GPT-5.5 | $5.00 | $30.00 | 1.05M | Yes | Subscription + usage |
| Anthropic | Claude Opus 4.8 | $5.00 | $25.00 | 1M | Yes | Subscription + usage |
| Gemini 3.5 Flash | $1.50 | $9.00 | 1.05M | Yes | Subscription + usage |
Pricing as of June 2026
Buy credit packs starting at $10. Credits never expire.
curl https://api.list-cloud.com/v1/chat/completions \
-H "Authorization: Bearer lc-sk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "list-sclak-v1",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'No onboarding calls. No sales team. Create an account, buy credits, and start.
Create Free Account