Routin is an OpenAI-compatible AI API gateway that helps developers access multiple model providers through one API, with routing, usage analytics and transparent billing.

Which AI model families can teams compare on Routin?

Routin highlights current model families such as GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, Claude Fable 5, claude-fable-5, GPT-5.5, GPT-5.4 mini, Claude Opus 4.8, Claude Sonnet 5, Gemini 3.5 Flash, Gemini 3.1 Pro Preview, DeepSeek Reasoner, Qwen3.7 Max, Grok 4.3, Mistral Medium 3.5, Mistral OCR 4 and other OpenAI-compatible chat, reasoning, image, audio, video and embedding models.

Can Routin work with OpenAI-compatible SDKs and coding agents?

Yes. Routin is designed for OpenAI-compatible integrations, including OpenAI SDK based apps, Codex, Claude Code, Cursor, Cline and other developer tools that can use a custom base URL and API key.

Does Routin show AI API pricing and context windows?

The public model catalog includes model provider metadata, pricing units, context windows, model types and token-based billing information where available.

What is the claude-haiku-4-5 API used for?

claude-haiku-4-5 is listed on Routin as a chat. Developers can evaluate its provider, context window, pricing fields and OpenAI-compatible access for production AI apps and agents.

Who provides claude-haiku-4-5?

claude-haiku-4-5 is associated with Anthropic in the Routin model catalog when provider metadata is available.

How do I call claude-haiku-4-5 with an OpenAI-compatible client?

Create a Routin API key, set your OpenAI-compatible client base URL to the Routin API endpoint, and use claude-haiku-4-5 as the model name when making chat, response or modality-specific requests supported by the model.

How is claude-haiku-4-5 pricing evaluated?

Routin surfaces available pricing metadata for claude-haiku-4-5, including input price, output price, billing unit, context tiers and cache-related prices when the provider exposes them.

<Back to Models

chat

Anthropic

claude-haiku-4-5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

Pricing	Billing mode
Prompt	¥0.5000/1M tokens
Output	¥2.5000/1M tokens
5m cache write	¥0.6250/1M tokens
Cache hit	¥0.0500/1M tokens