LLM API
320+ language models from 48 labs on one OpenAI-compatible endpoint and one API key.
Start in a minute
The Imagera LLM API is one OpenAI-compatible endpoint, https://api.imagera.ai/llm/v1, that serves 320+ language models from 48 labs with a single Imagera API key, billed per token from your Imagera balance.
Point any OpenAI client at Imagera and switch models by changing one string. Every model in the table answers on the same endpoint, with the same key you use for Imagera's image, video and audio API.
https://api.imagera.ai/llm/v1322 models from 48 labs. 275 take tool calls and 201 read images.
curl https://api.imagera.ai/llm/v1/chat/completions \
-H "Authorization: Bearer $IMAGERA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-5.3-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'Browse by what you need
Groups come from each model’s own capabilities and price. Artwork is illustration.
Browse by lab
49 labs. The full list is in the lab filter below.
All models and prices
Price per million tokens. Open a model for its limits and a ready request.
322 models, page 1 of 14
| Model | Lab | Context | Input | Output | Tier |
|---|---|---|---|---|---|
| OpenAI | 1.1M | $2.00 | $10.00 | Premium | |
| OpenAI | 1.1M | $2.00 | $10.00 | Premium | |
| OpenAI | 1.1M | $4.00 | $20.00 | Premium | |
| OpenAI | 1.1M | $4.00 | $20.00 | Premium | |
| OpenAI | 1.1M | $0.20 | $1.00 | Budget | |
| OpenAI | 1.1M | $0.20 | $1.00 | Budget | |
| OpenAI | 1.1M | $4.00 | $20.00 | Premium | |
| OpenAI | 1.1M | $4.00 | $20.00 | Premium | |
| OpenAI | 1.1M | $20.00 | $100.00 | Premium | |
| OpenAI | 1.1M | $20.00 | $100.00 | Premium | |
| OpenAI | 1.1M | $0.40 | $2.40 | Standard | |
| OpenAI | 1.1M | $0.40 | $2.40 | Standard | |
| OpenAI | 1.1M | $4.00 | $24.00 | Premium | |
| OpenAI | 1.1M | $4.00 | $24.00 | Premium | |
| OpenAI | 1.1M | $8.00 | $40.00 | Premium | |
| OpenAI | 1.1M | $8.00 | $40.00 | Premium | |
| OpenAI | 400K | $10.00 | $60.00 | Premium | |
| OpenAI | 1.1M | $60.00 | $360.00 | Premium | |
| OpenAI | 1.1M | $10.00 | $60.00 | Premium | |
| OpenAI | 400K | $0.40 | $2.50 | Standard | |
| OpenAI | 400K | $1.50 | $9.00 | Premium | |
| OpenAI | 1.1M | $60.00 | $360.00 | Premium | |
| OpenAI | 1.1M | $5.00 | $30.00 | Premium | |
| OpenAI | 400K | $3.50 | $28.00 | Premium |
How billing works
Per token, from your balance
Input tokens are charged at the input price, the reply at the output price, and cached input at the cached rate where a model has one. The total comes off your Imagera balance when the reply ends.
Nothing for a call that never ran
If no route can serve a request, it fails with a clear error and nothing is charged.
Prices follow the labs
Prices are read from the providers’ own lists. When a lab changes a price, the table and your next call follow it.
Questions
Which SDKs and tools work with it?
Anything that speaks the OpenAI Chat Completions API: the official OpenAI SDKs for Python and JavaScript, LangChain, LlamaIndex, Vercel AI SDK and editors that accept a custom OpenAI base URL. Set the base URL and your Imagera API key; nothing else changes.
Does it stream?
Yes. Send "stream": true and tokens arrive as server-sent events, the same format the OpenAI SDKs read. Token usage is reported at the end of the stream.
What happens when a provider is down?
Each model can be served on more than one route. If a route fails before the first token, the request moves to the next one automatically, so a single outage does not reach your app. Once tokens are streaming, a call is never retried, so it is never charged twice.
Do tool calls, images and JSON output work?
Where the model supports them. Use the filters above the table: 274 models take tool calls (function calling) and 199 accept images in the messages. JSON output follows the OpenAI response_format field.
Where do I get a key?
Create one on the API keys page. The same key works for language models and for every image, video and audio model in the Imagera API.
How do I choose a model?
Filter by what your app needs (tool calling, image input, reasoning), then sort by price or context size. To see how models answer the same prompt side by side before you commit, use the LLM Arena.