Free Kilo Code API Key, Base URL & Rate Limits
API ProviderKilo Code is a coding-specific API gateway that routes requests to the best available coding model — ByteDance Seed, Grok Code Fast, NVIDIA Nemotron, and Arcee Trinity.
How to get a free Kilo Code API key
- 1
- 2 Go to API Keys
- 3 Generate an API key
- 4 Let the router pick Kilo Code auto-routes to the best coding model. No model selection needed.
- 5 Configure OpenAI client Base URL: https://api.kilo.ai/api/gateway
Provider Snapshot
Supported Models 10 models
View in directory →| Model ID | Developer | Context | Availability | Free Tier | Use cases |
|---|---|---|---|---|---|
| tencent/hy3 tencent/hy3:free | Tencent | 262K | Online | Free tier | chat |
| nvidia/nemotron-3-ultra-550b-a55b:free nvidia/nemotron-3-ultra-550b-a55b:free | Kilo Code | 1.0M | Online | Free tier | chatreasoning |
| stepfun/step-3.7-flash:free stepfun/step-3.7-flash:free | StepFun | 262K | Online | Free tier | chat |
| nvidia/nemotron-3.5-lightning:free nvidia/nemotron-3.5-lightning:free | NVIDIA | 1.0M | Online | Free tier | chatreasoning |
| poolside/laguna-s-2.1:free poolside/laguna-s-2.1:free | Kilo Code | 262K | Online | Free tier | chat |
| poolside/laguna-xs-2.1:free poolside/laguna-xs-2.1:free | Kilo Code | 262K | Online | Free tier | chat |
| cohere/north-mini-code:free cohere/north-mini-code:free | Cohere | 256K | Online | Free tier | chatcoding |
| nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free | Kilo Code | 256K | Online | Free tier | chatvisionreasoning |
| liquid/lfm-2.5-2.6b:free liquid/lfm-2.5-2.6b:free | Liquid AI | 64K | Online | Free tier | chat |
| nvidia/nemotron-3-super-120b-a12b:free nvidia/nemotron-3-super-120b-a12b:free | Kilo Code | 262K | Online | Free tier | chatreasoning |
Developer Tools
Related Providers
View all →Kilo Code FreeLLM Score free API access score
How we score →What is Kilo Code?
Coding-optimized API gateway — routes to the best coding model.
Kilo Code is a coding-specific API gateway that routes requests to the best available coding model — ByteDance Seed, Grok Code Fast, NVIDIA Nemotron, and Arcee Trinity. Purpose-built for AI code editors. Free tier offers ~200 requests/hour. OpenAI-compatible.
- Coding-optimized model routing
- ByteDance Seed, Grok Code, Nemotron
- ~200 req/hr free
- Purpose-built for VS Code & AI editors
API Compatibility: OpenAI SDK-compatible (Chat Completions)
Kilo Code Free Tier Limits & Pricing
Kilo Code API Setup Tutorials
Kilo Code is fully compatible with popular AI coding assistants like Cursor, Claude Code, and more. To see step-by-step API configuration instructions for your favorite tool, please visit our Global Configuration Guide →
Kilo Code Model Use Cases
What Kilo Code's free models are best for, based on aggregated model capabilities:
Kilo Code Limitations & Caveats
- Coding-optimized only — not suitable for general chat or reasoning
- Model routing is opaque — you don't control which model serves your request
- ~200 req/hr may be limiting for heavy CI/CD or batch use
Kilo Code FAQ
How does Kilo Code choose which model to use?
Kilo Code automatically routes your request to the best available coding model based on current availability and performance. You don't select a specific model — the gateway handles it.
Can I use Kilo Code for non-coding tasks?
Kilo Code is optimized specifically for code generation. It may work for general text tasks, but results won't be as good as a general-purpose provider. Use Groq or OpenRouter for non-coding workloads.
Is Kilo Code the same as the Kilo VS Code extension?
Yes — Kilo Code is the AI coding extension for VS Code/Cursor, and their API gateway powers the backend. You can use the same API key in both the extension and direct API calls.