All your AI models
in one place
Models from the world's top AI labs
OpenAI
Anthropic
Google
DeepSeek
Meta
Mistral
xAI
Alibaba
Build an AI app
on top of Hostlinku API
Playground and Hostlinku run on the same LLM API endpoint that you use: Chat Completions, Responses, and Anthropic Messages. Use the same API key and balance for summarization, text generation, tool calls, and Q&A in your application.
Drop-in integration, compatible with OpenAI
Are you already using OpenAI SDK? Just change the base URL and the string model. The gateway automatically translates message formats between providers.
- Compatible with OpenAI SDK (drop-in base URL)
- Streaming via Server-Sent Events
- Function calling, JSON mode & structured outputs
- TypeScript & Python SDK
- Webhook events & idempotency keys
curl -N https://api.hostlinku.com/v1/chat/completions \
-H "Authorization: Bearer $HOSTLINKU_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "claude-sonnet-4-5", "stream": true, "messages": [{ "role": "user", "content": "Halo!" }] }'Everything you need in one gateway
Explore 40 AI Models from the best labs
Claude, GPT, GLM, DeepSeek, Qwen, Kimi, and others. One API, one bill.
Transparent pricing, per token
Compare input/output and context window values. Click for model details.
Claude Opus 5.5
Input
$3.52
Output
$17.6
GPT-6.1 Sol
Input
$1.76
Output
$8.8
DeepSeek-V4.1-Flash
Input
$0.132
Output
$0.528
GLM 5.3
Input
$1.04
Output
$3.62
Qwen 3.6 Plus
Input
$0.2587
Output
$1.55
Kimi K3
Input
$2.59
Output
$12.94
Claude Opus 5
Input
$4.4
Output
$22
Claude Sonnet 5
Input
$1.76
Output
$8.8
Claude Fable 5
Input
$2.5
Output
$12.48
Claude Opus 4.8
Input
$4.4
Output
$22
Claude Opus 4.7
Input
$4.4
Output
$22
Claude Haiku 4.5
Input
$0.88
Output
$4.4
Use Hostlinku Everywhere
Use Hostlinku in the tools you already use: IDE, CLI, agent, and SDK.
Additional Features
Prompt Library
Save and reuse prompt templates for team workflows. Maintain consistency across models and integrations.
Real-Time Monitoring
Monitor the performance, latency, and reliability of each endpoint directly from the dashboard.
Multimodal
Support for text, image, and document input for models that support vision and input files.
Request History
Request history is stored for auditing and debugging. View the payload, response, and usage for each request.
Import Content
Easily import PDFs, images, and documents. Use AI to ask questions, extract information, and summarize documents.
Multilingual
The model supports more than 100 languages, including Indonesian, to meet global product needs.
One gateway, all models,
transparent fees
You can monitor the price, performance, and usage yourself.
One API for all models
Access Claude, GPT, Gemini, DeepSeek, and 53, along with other models, through a single endpoint compatible with OpenAI and Anthropic.
- Drop-in: Just change the base URL
- Streaming & tool calling
- Automatic failover between providers
Pay per token. No subscription required.
Top up your balance once, and use it for all models. There are no monthly fees, minimum usage requirements, or per-seat charges.
- Open price per token
- Prompt caching to save costs
- One balance, one bill
All usage can be monitored
Request logs, token usage, latency, and costs per API key are displayed in real time in the Console, along with the public gateway status.
- Request logs & history
- Scope and Limits for API Keys
- Public Service Status
From prototype to production, without switching accounts. Start at Playground, continue in the IDE or CLI, and scale using the SDK with the same API key and balance.
