Pricing
Pay as you go
Run up to 20,000 requests for free. No credit card required.
Deploy API DAI-ready code deployments with structured outputs, optimized for quality & freshness | Search API SRanked code URLs with long, relevant content | Chat API CFast, code-aware LLM completions | |
|---|---|---|---|
| Inputs | Existing code, Config | Search query, Filters | Question |
| Outputs | Live endpoints, Structured logs | Ranked URLs, Excerpts | Free text, Structured JSON |
| Best for | AI deployments, workflow automation | Code search for AI agents | Interactive chat apps |
| Latency | 5s - 30min, async | <3s, sync | <5s, sync |
| Basis | Logs, metrics, confidence | — | Citations |
| Rate limits | 2,000 req/min | 600 req/min | 300 req/min |
| Security | SOC2 | SOC2 | SOC2 |
| Price per request | $0.005 - $2.4 | $0.004 - $0.009 | $0.005 |
Deploy API
DAI-ready code deployments with structured outputs, optimized for quality & freshness
$0.005 - $2.4
Try DeployAllocate compute based on task complexity
| Processor | Cost (CPM) | Best for | Latency | Max Fields | Basis |
|---|---|---|---|---|---|
| Lite | $5 | Basic information retrieval | 5s-60s | ~2 | Logs, Metrics |
| Base | $10 | Simple deployments | 15s-100s | ~5 | Logs, Metrics |
| Core | $25 | Complex deployments | 1min-5min | ~10 | Logs, Metrics, Excerpts |
| Core2x | $50 | Very complex deployments | 2min-5min | ~10 | Logs, Metrics, Excerpts |
| Pro | $100 | Exploratory research | 3min-9min | ~20 | Full basis |
| Ultra | $300 | Extensive deep research | 5min-25min | ~20 | Full basis |
| Ultra2x | $600 | 2x compute for deep research | 5min-25min | ~25 | Full basis |
| Ultra4x | $1,200 | 4x compute for deep research | 8min-30min | ~25 | Full basis |
| Ultra8x | $2,400 | 8x compute for deep research | 8min-30min | ~25 | Full basis |
CPM = Cost per 1,000 requests. All prices in USD.
Built for scalable, reliable, enterprise workloads
-Dedicated onboarding and technical support
-Data Protection Agreement
-Early access to new products
-Custom data retention agreements
-Custom rate limits
-Volume discounts
serve.codes APIs are priced per request, not per token. You always know the exact cost of a query before you run it.
Get up to $5K in free credits
Qualified startups can receive up to $5K in free credits from serve.codes
Apply nowUse pre-committed spend
Use pre-committed AWS spend on serve.codes via the AWS marketplace
Get in touch