cctk.ai
Sign in Sign up
Multi-model gateway + ops console

One API. Every model provider.

Open console
One unified endpoint TK-based balance · official per-token rates Logs · usage · billing
Core capabilities

One clean layer between your application and many model providers.

Exact-model passthrough

Unified API surface

Traffic visibility

Scoped access

Provider overview

Leading frontier providers supported, with more on the way.

A
Anthropic Claude
Messages API · OpenAI-compat
  • claude-opus-4-8
  • claude-sonnet-4-6
  • claude-haiku-4-5
200K contextExtended ThinkingTool useVision
O
OpenAI GPT
Chat Completions · Responses API
  • gpt-5.5
  • gpt-5.4-mini
  • gpt-image-2
ReasoningTool useVision & audioImage gen
G
Google Gemini
generateContent · OpenAI-compat
  • gemini-2.5-flash
  • gemini-3.1-pro-preview
  • gemini-3-pro-image-preview
  • gemini-3.1-flash-image
1M contextMultimodalCodeTool use
+
More providers
On the roadmap
  • …and more on request
Compatibility

Compatible with the AI providers and tools you already use

CC
Claude Code
Anthropic CLI
CX
Codex CLI
OpenAI CLI
CD
Codex Desktop
OpenAI desktop
OC
OpenCode
Terminal agent
CS
Cherry Studio
Desktop client
CB
ChatBox
Cross-platform client
SDKs & frameworks OpenAI SDK Anthropic SDK Gemini SDK Vercel AI SDK LangChain LangGraph LlamaIndex LiteLLM curl
Usage flow

From provider setup to a stable gateway surface in four steps

Register an account

Top up balance

Create an API key

Use the key

Trusted by developers

Built for teams that operate real model traffic.

100M+
API requests processed
10,000+
Developers onboarded
3+
Model providers connected
98.9%
Platform uptime
S
Sarah Chen
ML Platform Lead
M
Marcus Rivera
Backend Engineer
A
Aisha Patel
AI Infrastructure Engineer
Pricing

Token-precise billing. TK-based balance. Group multipliers visible upfront.

TK balance · per-group multipliers · no hidden surcharges

How a charge is computed

cost in TK = official_rate_per_token × tokens × group_multiplier
e.g. claude-opus-4-8 · no cache
Input rate $5.00 / 1M
Output rate $25.00 / 1M
Group multiplier × 2.1
Each turn re-sends a 1M-token context
Official cost $5.00
Per-turn charge 10.5 TK
e.g. claude-opus-4-8 · with cache
Input rate $5.00 / 1M
Output rate $25.00 / 1M
Cache write · 5m $6.25 / 1M
Cache read $0.50 / 1M
Group multiplier × 2.1
Reusing a 1M-token context
First turn · cache write 13.13 TK
Each later turn · cache read 1.05 TK
  • ¥1 = 1 TK, where 1 TK settles 1 USD of token cost
  • Per-token rate mirrors the upstream provider's official rate
  • Each group has a transparent multiplier (e.g. Claude 2.1× · GPT-Pro 0.6×)
  • No monthly minimum, no subscription, no lock-in — pay only as you go
  • Multipliers shown on the model card; constant until announced
  • Routing, scoped keys, request logs, usage analytics all included
Open the console →
FAQ

Questions teams ask before putting a gateway in front of production traffic.

What is cctk.ai?
How is it different from calling providers directly?
Are the models genuine, not swapped for cheaper ones?
Which payment methods are supported?
Is it secure to use?

One endpoint. Every model.

Start now →