LLM API
UnificAlly serves 43 large language models from Anthropic, OpenAI, xAI, Google, DeepSeek, Cursor and Moonshot AI through one API key. Rates start at $0.015 per 1M input tokens (GPT 6 Luna), billed per token from a prepaid balance with no subscription. Call any of them in the OpenAI format at /v1/chat/completions or the Anthropic format at /v1/messages, with streaming and tool use.
All 43 LLMs on UnificAlly
| Model | Provider | Starting rate |
|---|---|---|
| Claude Haiku 5.5 API Anthropic 1M context, 128k output, 72.4% OSWorld 2.1, the first Haiku with adaptive thinking. | Anthropic | from $0.0495 in / $0.2475 out per 1M tokens |
| GPT 6.1 Sol API OpenAI Near-Astra coding and computer use at a fifth of Astra's price, 75.2% DeepSWE, 1M context, cached input at half GPT 6 Sol's rate. | OpenAI | from $0.3 in / $1.5 out per 1M tokens |
| Claude Sonnet 5.5 API Anthropic 1M context, 128k output, 70.6% Terminal-Bench 4.0, 30%+ faster than Sonnet 5. | Anthropic | $0.99 in / $4.95 out per 1M tokens |
| GPT 6 Luna API OpenAI OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5. | OpenAI | from $0.015 in / $0.075 out per 1M tokens |
| GPT 6 Sol API OpenAI 1M context, image input, 56.4% Agents' Last Exam at 60% less per task than Opus 5, half the price of GPT 5.6 Sol. | OpenAI | from $0.3 in / $1.5 out per 1M tokens |
| Claude Opus 5.5 API Anthropic 1M context, 128k output, 66.4% Terminal-Bench 4.0. | Anthropic | $1 in / $5 out per 1M tokens |
| DeepSeek V4 Flash API DeepSeek Versioned V4 Flash ID, now answered by V4.1 Flash. 1M context, 384K max output. | DeepSeek | $0.1125 in / $0.45 out per 1M tokens |
| DeepSeek V4 Pro API DeepSeek 1.6T MoE with 49B active, 1M context, 384K max output, thinking on by default. | DeepSeek | $0.51 in / $1.52 out per 1M tokens |
| DeepSeek V4.1 Flash API DeepSeek 1M context, 384K max output, 552B MoE with 16B active, 74.2% DeepSWE v1.1. | DeepSeek | $0.1125 in / $0.45 out per 1M tokens |
| Grok 4.7 API xAI 500k context, image input, four reasoning efforts, 46.3% CursorBench 4.0, #5 Harvey Legal Agent. | xAI | $0.3 in / $0.9 out per 1M tokens |
| GPT 6 Astra API OpenAI 1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam. | OpenAI | from $1.5 in / $7.5 out per 1M tokens |
| Gemini 3.5 Flash API 1M context, 5 reasoning efforts incl. minimal, 83.6% MCP Atlas, 57.9% Finance Agent v2, 189 tok/s. | $0.45 in / $2.7 out per 1M tokens | |
| Claude Fable 5.1 API Anthropic 1M context, 128k output, 55.8% Terminal-Bench 4.0, 90.0% ARC-AGI-2. | Anthropic | $6.25 in / $31.25 out per 1M tokens |
| Gemini 3.8 Flash API 1M context, four reasoning efforts, 73.7% DeepSWE v1.1, 89.4% Terminal-Bench 2.1, 305 tok/s. | $0.225 in / $1.125 out per 1M tokens | |
| Grok 4.5 API xAI 500k context, image input, three reasoning efforts, 79.3% Terminal-Bench 2.1, trained with Cursor. | xAI | $0.3 in / $0.9 out per 1M tokens |
| Grok 4.3 API xAI 1M context, image input, four reasoning efforts incl. none, 115.8 tok/s, 98% Tau2-Bench Telecom. | xAI | $0.1875 in / $0.375 out per 1M tokens |
| Grok Build 0.1 API xAI 256k context, image input, agentic coding with function calling and MCP, 0.53s first token. | xAI | $0.15 in / $0.3 out per 1M tokens |
| Grok 4.20 Reasoning API xAI 1M context, image input, thinking on, agentic tool calling, 98.9 tok/s, 72.2% SWE-bench Verified. | xAI | $0.1875 in / $0.375 out per 1M tokens |
| Grok 4.20 Non-Reasoning API xAI 1M context, image input, no thinking phase, 0.64s first token, 95.8 tok/s, agentic tool calling. | xAI | $0.1875 in / $0.375 out per 1M tokens |
| Grok 4.20 Multi-Agent API xAI Leader agent plus 4 or 16 sub-agents in parallel, 1M context, image input, Responses API only. | xAI | $0.1875 in / $0.375 out per 1M tokens |
| Grok 4.6 API xAI 500k context, image input, four reasoning efforts, 95.6% SWE-bench Verified, #1 CursorBench 3.2. | xAI | $0.3 in / $0.9 out per 1M tokens |
| Gemini 3.7 Flash API 1M context, 64k output, text/image/audio/video input, ~340 tok/s, 97% MRCR long-context recall. | $0.225 in / $1.125 out per 1M tokens | |
| Gemini 3.6 Flash API 1M context, 65k output, multimodal input, 83% OSWorld-Verified, 234 tok/s output speed. | $0.45 in / $2.25 out per 1M tokens | |
| Claude Opus 5 API Anthropic 1M context, 128k output, image input, 43.3% Frontier-Bench v0.1, 30.2% ARC-AGI 3. | Anthropic | $1.25 in / $6.25 out per 1M tokens |
| Kimi K3 API Moonshot AI 2.8T parameters, open weights, 1M context, 131k default output, always-on thinking. | Moonshot AI | $2.25 in / $11.25 out per 1M tokens |
| GPT 5.6 Sol API OpenAI 1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode. | OpenAI | from $0.75 in / $4.5 out per 1M tokens |
| GPT 5.6 Terra API OpenAI 1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam. | OpenAI | from $0.375 in / $2.25 out per 1M tokens |
| GPT 5.6 Luna API OpenAI Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding. | OpenAI | from $0.15 in / $0.9 out per 1M tokens |
| Claude Fable 5 API Anthropic 1M context, 128k output, text and image input, adaptive thinking, top Arena Text and Vision rank. | Anthropic | $6.25 in / $31.25 out per 1M tokens |
| Claude Sonnet 4.5 API Anthropic 200k context, 64k output, 77.2% SWE-bench Verified, 61.4% OSWorld, extended thinking. | Anthropic | See model page |
| Claude Opus 4.5 API Anthropic 200k context, 64k output, 80.9% SWE-bench Verified, effort controls from low to high. | Anthropic | See model page |
| Claude Haiku 4.5 API Anthropic 200k context, 64k output, 73.3% SWE-bench Verified, 50.7% OSWorld, extended thinking. | Anthropic | $0.25 in / $1.25 out per 1M tokens |
| Claude Sonnet 4.6 API Anthropic 1M context, 128k output, 79.6% SWE-bench Verified, 72.5% OSWorld, adaptive thinking. | Anthropic | $0.75 in / $3.75 out per 1M tokens |
| Claude Opus 4.6 API Anthropic 1M context, 128k output, effort controls, top Arena Document and Search rank. | Anthropic | $1.25 in / $6.25 out per 1M tokens |
| Claude Sonnet 5 API Anthropic Agentic coding, 1M context, 128k output, image input, 85.2% SWE-bench Verified. | Anthropic | $0.75 in / $3.75 out per 1M tokens |
| Claude Opus 4.7 API Anthropic 1M context, 128k output, 87.6% SWE-bench Verified, 78% OSWorld, 2576px image input. | Anthropic | $1.25 in / $6.25 out per 1M tokens |
| Claude Opus 4.8 API Anthropic 1M context, 128k output, 88.6% SWE-bench Verified, 83.4% OSWorld, adaptive thinking. | Anthropic | $1.25 in / $6.25 out per 1M tokens |
| GPT 5.4 API OpenAI Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents. | OpenAI | $0.375 in / $2.25 out per 1M tokens |
| GPT 5.5 API OpenAI 1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2. | OpenAI | $0.75 in / $4.5 out per 1M tokens |
| GPT 5.4 Mini API OpenAI 400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini. | OpenAI | See model page |
| GPT 5.4 Nano API OpenAI 400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh. | OpenAI | See model page |
| Composer 2.5 API Cursor Agentic coding, 79.8% SWE-Bench Multilingual, 69.3% Terminal-Bench 2.0, tuned for long agent runs. | Cursor | $0.05 in / $0.25 out per 1M tokens |
| Composer 2.5 Fast API Cursor Low-latency default variant of Composer 2.5, same intelligence, 79.8% SWE-bench Multilingual. | Cursor | $0.3 in / $1.5 out per 1M tokens |
How to call the LLM API
Use your UnificAlly API key and any model ID from the table. Existing OpenAI clients only need the base URL changed to https://api.unifically.com/v1.
curl -X POST https://api.unifically.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "anthropic/claude-sonnet-4-6",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'LLM API FAQ
- How much does the LLM API cost?
- Each model has its own input and output rate per 1M tokens, shown in the table above and on the pricing page. The lowest input rate right now is $0.015 per 1M input tokens (GPT 6 Luna). You pay per token from a prepaid balance: no subscription, no monthly minimum, and the balance does not expire.
- Does the LLM API work with the OpenAI and Anthropic SDKs?
- /v1/chat/completions follows the OpenAI Chat Completions format and works for every model in the table except Responses-only models such as Grok 4.20 Multi-Agent. /v1/messages follows the Anthropic Messages format and /v1/responses the OpenAI Responses format; which models support each is listed in the docs. Streaming and tool use work.
- How do I move an existing app to UnificAlly?
- Point your OpenAI client at https://api.unifically.com/v1, use a UnificAlly API key, and set model to an ID from the table, such as anthropic/claude-sonnet-4-6. Anthropic SDK code keeps its request shape on /v1/messages. One key and one balance cover every model.
- Can I try these LLMs 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 outputs before writing any code.