Clark Platform

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.

Base URL: https://www.clarkchat.com/v1 · Bearer API key

Capabilities

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.

Pricing highlights

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.

Get an API key