OpenAI API
UnificAlly serves 13 OpenAI models through one API key: 11 language models and 2 image models. Language models start at $0.015 per 1M input tokens (GPT 6 Luna). Image models start at $0.03 per image (GPT Image 2.5). 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; the image models take POST /v1/tasks with a model ID and an input object.
UnificAlly is an independent API, not affiliated with or endorsed by OpenAI: you use a UnificAlly API key and balance, not an account with OpenAI.
All 13 OpenAI models on UnificAlly
| Model | Type | Starting rate |
|---|---|---|
| GPT 6.1 Sol API LLM 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. | LLM | from $0.3 in / $1.5 out per 1M tokens |
| GPT 6 Luna API LLM OpenAI's cheapest GPT-6, 1M context, 66.6% DeepSWE for $0.22 a task, 93% less than Opus 5. | LLM | from $0.015 in / $0.075 out per 1M tokens |
| GPT 6 Sol API LLM 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. | LLM | from $0.3 in / $1.5 out per 1M tokens |
| GPT 6 Astra API LLM 1M context, image input, effort up to max, 58.2% Terminal-Bench 4.0, 59.3% Agents' Last Exam. | LLM | from $1.5 in / $7.5 out per 1M tokens |
| GPT 5.6 Sol API LLM 1M context, 128k output, 88.8% Terminal-Bench 2.1, 80 Coding Agent Index, ultra subagent mode. | LLM | from $0.75 in / $4.5 out per 1M tokens |
| GPT 5.6 Terra API LLM 1M context, 128k output, 77.4 Coding Agent Index, beats Fable 5 on Agents' Last Exam. | LLM | from $0.375 in / $2.25 out per 1M tokens |
| GPT 5.6 Luna API LLM Fastest GPT 5.6, 1M context, beats Fable 5 on Agents' Last Exam, ahead of Opus 4.8 on coding. | LLM | from $0.15 in / $0.9 out per 1M tokens |
| GPT 5.5 API LLM 1M context, 128k output, 82.7% Terminal-Bench 2.0, 78.7% OSWorld, 85% ARC-AGI-2. | LLM | $0.75 in / $4.5 out per 1M tokens |
| GPT 5.4 API LLM Native computer use, 75% OSWorld-Verified, up to 1M context, 128k output, tool search for agents. | LLM | $0.375 in / $2.25 out per 1M tokens |
| GPT 5.4 Mini API LLM 400k context, 128k output, 54.4% SWE-Bench Pro, 72.1% OSWorld, over 2x faster than GPT-5 mini. | LLM | See model page |
| GPT 5.4 Nano API LLM 400k context, 128k output, 52.4% SWE-Bench Pro, 82.8% GPQA Diamond, effort levels none to xhigh. | LLM | See model page |
| GPT Image 2.5 API text-to-image Flare for speed, Sunburst for edit precision: 1K/2K/4K, 15 aspect ratios, 16 reference images, transparent output. | text-to-image | from $0.03 per image |
| GPT Image 2 API text-to-image T2I or reference editing, 5 aspect ratios, 1K, 2K, or 4K resolution control. | text-to-image | from $0.03 per image |
How to call the OpenAI 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.
OpenAI format: POST /v1/chat/completions
curl -X POST https://api.unifically.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "openai/gpt-6.1-sol",
"messages": [
{"role": "user", "content": "Review this pull request and list any bugs you find."}
]
}'Image and video models: POST /v1/tasks
# 1. Start a task
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "openai/gpt-image-2",
"input": {
"prompt": "A serene mountain landscape",
"aspect_ratio": "16:9",
"resolution": "2K"
}
}'
# 2. Read the result with the task_id from step 1
curl https://api.unifically.com/v1/tasks/TASK_ID \
-H "Authorization: Bearer YOUR_API_KEY"OpenAI API FAQ
- Is this the official OpenAI API from OpenAI?
- No. UnificAlly is an independent API that serves OpenAI's models; it is not affiliated with or endorsed by OpenAI. 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 OpenAI 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 $0.015 per 1M input tokens (GPT 6 Luna). Image models start at $0.03 per image (GPT Image 2.5). You pay per token or per generation from a prepaid balance: no subscription, no monthly minimum, and the balance does not expire. Failed generations are not charged.
- Is this the same request format as the ChatGPT API?
- "ChatGPT API" is the common name for OpenAI's Chat Completions API. UnificAlly's /v1/chat/completions takes the same request and returns the same response shape, so the OpenAI SDKs work after changing the base URL to https://api.unifically.com/v1 and the API key. GPT Image 2.5 and GPT Image 2 run on the same key through POST /v1/tasks.
- How do I move existing OpenAI SDK code to UnificAlly?
- Point your OpenAI client at https://api.unifically.com/v1, use a UnificAlly API key and set model to an ID such as openai/gpt-6.1-sol (each model page lists its ID). Nothing else in the request changes.
- Can I try the GPT 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.