Clark-managed agents and supported models, behind one API.
Point an OpenAI-compatible client at Clark and choose Claude Opus 5, Kimi K3, GPT-5.6, or a Clark-managed agent. Your app keeps the SDK it already has; Clark handles the rest.
One gateway, two ways to run.
Choose who runs the tools: hand the whole job to Clark Agent, or keep the loop in your app and use Clark as a model gateway.
-
Clark Agent as an API
Set model to "clark" or "clark_max" and Clark owns the loop: planning, durable memory, built-in search and browsing, a managed computer, parallel specialist agents, and verified artifacts.
-
Full passthrough
Choose a supported "provider/model" ID and your app runs the tool calls while Clark handles model routing and retries.
-
OpenAI-compatible
Chat completions and responses work with the OpenAI client you already use. Change the base URL and API key; keep your code.
-
Files, memories, and code
API resources cover models, responses, chat completions, files, memories, and code repositories.
-
Official SDKs
TypeScript, JavaScript, Python, Rust, and Zig clients, plus a copyable integration brief for coding agents.
-
Per-token pricing
Pay per token on each supported full-passthrough model. Cache pricing and live rates are in the app.
Supported passthrough models, per 1M tokens.
| Model | Input · $ / 1M tokens | Output · $ / 1M tokens |
|---|---|---|
| Claude Opus 5 | $6 | $30 |
| Claude Opus 5 Fast | $12 | $60 |
| Kimi K3 | $3.60 | $18 |
| GPT-5.6 Luna | $1.20 | $7.20 |
| GPT-5.6 Terra | $3 | $18 |
| GPT-5.6 Sol | $6 | $36 |
| GLM 5.2 | $2.40 | $6 |
| Kimi K2.7 Code | $0.86 | $4.19 |
| Grok 4.5 | $2.40 | $7.20 |
| DeepSeek V4 Flash Latest | $0.11 | $0.22 |
| DeepSeek V4 Pro | $0.52 | $1.04 |
| Gemini 3.5 Flash-Lite | $0.36 | $3 |
Prices are what you pay through the Clark gateway. Sign in for managed-agent selections, cache pricing, and live rates.
Get started
Create an API key and make your first call.