Claude API
UnificAlly serves 14 Anthropic models through one API key: 14 language models. Language models start at $0.0495 per 1M input tokens (Claude Haiku 5.5). Everything is billed from a prepaid balance with no subscription.
Call the language models in the OpenAI format at /v1/chat/completions or the Anthropic format at /v1/messages, with streaming and tool use.
UnificAlly is an independent API, not affiliated with or endorsed by Anthropic: you use a UnificAlly API key and balance, not an account with Anthropic.
All 14 Anthropic models on UnificAlly
| Model | Type | Starting rate |
|---|---|---|
| Claude Haiku 5.5 API LLM 1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking. | LLM | from $0.0495 in / $0.2475 out per 1M tokens |
| Claude Sonnet 5.5 API LLM 1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5. | LLM | $0.99 in / $4.95 out per 1M tokens |
| Claude Opus 5.5 API LLM 1M context, 128k output, 66.4% Terminal-Bench 4.0. | LLM | $1 in / $5 out per 1M tokens |
| Claude Fable 5.1 API LLM 1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2. | LLM | $6.25 in / $31.25 out per 1M tokens |
| Claude Opus 5 API LLM 1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3. | LLM | $1.25 in / $6.25 out per 1M tokens |
| Claude Fable 5 API LLM 1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank. | LLM | $6.25 in / $31.25 out per 1M tokens |
| Claude Sonnet 5 API LLM Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified. | LLM | $0.75 in / $3.75 out per 1M tokens |
| Claude Opus 4.8 API LLM 1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking. | LLM | $1.25 in / $6.25 out per 1M tokens |
| Claude Opus 4.7 API LLM 1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input. | LLM | $1.25 in / $6.25 out per 1M tokens |
| Claude Sonnet 4.6 API LLM 1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking. | LLM | $0.75 in / $3.75 out per 1M tokens |
| Claude Opus 4.6 API LLM 1M context, 128k output, effort controls, top Arena Document and Search rank. | LLM | $1.25 in / $6.25 out per 1M tokens |
| Claude Sonnet 4.5 API LLM 200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking. | LLM | See model page |
| Claude Opus 4.5 API LLM 200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high. | LLM | See model page |
| Claude Haiku 4.5 API LLM 200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking. | LLM | $0.25 in / $1.25 out per 1M tokens |
How to call the Claude API
Use your UnificAlly API key and any model ID from the model pages. Existing OpenAI clients only need the base URL changed to https://api.unifically.com/v1.
Anthropic format: POST /v1/messages
curl -X POST https://api.unifically.com/v1/messages \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "anthropic/claude-sonnet-5-5",
"max_tokens": 1024,
"messages": [
{"role": "user", "content": "Explain quantum computing in one paragraph."}
]
}'Claude API FAQ
- Is this the official Claude API from Anthropic?
- No. UnificAlly is an independent API that serves Anthropic's models; it is not affiliated with or endorsed by Anthropic. You sign up with UnificAlly, create a UnificAlly API key and pay from a UnificAlly balance. The request formats are the same OpenAI and Anthropic formats, so existing code needs a new base URL, API key and model ID.
- How much does the Claude API cost on UnificAlly?
- Each model has its own rate, shown in the table above and on the pricing page. The lowest language model rate right now is $0.0495 per 1M input tokens (Claude Haiku 5.5). You pay per token from a prepaid balance: no subscription, no monthly minimum, and the balance does not expire. The Claude API pricing guide breaks the rates down model by model.
- Do extended thinking, tools and streaming work with the Claude API here?
- Yes. On /v1/messages, pass thinking as {"type": "adaptive"} for Claude 4.6 and newer models, or {"type": "enabled", "budget_tokens": N} for the Claude 4.5 models, and the response carries thinking blocks. Tools use the Anthropic format (name, description, input_schema), and stream: true returns server-sent events. The OpenAI format on /v1/chat/completions works for every Claude model too.
- How do I move existing Anthropic SDK code to UnificAlly?
- Keep the Anthropic SDK request shape, set the base URL to https://api.unifically.com and use a UnificAlly API key; model IDs look like anthropic/claude-sonnet-5-5 (each model page lists its ID). OpenAI SDK code works as well with the base URL https://api.unifically.com/v1.
- Can I try the Claude models before topping up?
- Yes. A new UnificAlly account starts with a $0.50 signup balance, and every model page has a browser playground that runs on it, so you can compare models before writing any code.