All plans include API access. Authenticate with your token key. Base URL is the same for every model.
OpenAI-compatible chat completions. Pass your API key in the Authorization header. Tool calls use the same tools / tool_choice fields as the OpenAI API. You run the tool on your side, then send the result back as a role: "tool" message.
| Field | Type | Description |
|---|---|---|
model | string | kimi-k3 · kimi-k2.6 · kimi-k2.5 · qwen3.8-max · qwen3.8-27b · qwen3-coder · qwen3.6-35b · qwen3.5-397b · deepseek-v4-pro · deepseek-v4-flash · deepseek-r1 · deepseek-v4.1-flash · deepseek-v3.2 · glm-5.3 · llama-4-maverick · llama-4-scout · mistral-large-3 · kolibri-1 · gemma-4-31b · mimo-v2.6-pro · gpt-oss-120b · realtime-voice · flux-1-schnell · sd-3.5 · qwen-image |
messages | array | Chat messages: role + content |
temperature | number | Optional, 0–2, default 0.7 |
max_tokens | number | Optional, response length limit |
tools | array | Optional. OpenAI-style tool definitions. The model may return a tool_calls message instead of plain text. |
tool_choice | string | Optional. auto (default), none, or a specific tool name. |
# Replace YOUR_KEY with the key from your account curl https://api.verall.org/v1/chat/completions \ -H "Authorization: Bearer YOUR_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "kimi-k3", "messages": [ {"role": "user", "content": "Explain anything without filters."} ] }'
import requests r = requests.post( "https://api.verall.org/v1/chat/completions", headers={ "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json", }, json={ "model": "kimi-k3", "messages": [ {"role": "user", "content": "Explain this without refusals."} ], }, ) print(r.json())
Same pattern as OpenAI: send tools, get tool_calls in the response, execute them yourself, send the tool result back. Works on the text models. Image model is generate/edit only.
import requests r = requests.post( "https://api.verall.org/v1/chat/completions", headers={ "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json", }, json={ "model": "kimi-k3", "messages": [ {"role": "user", "content": "What's the price of ticker AAPL?"} ], "tools": [{ "type": "function", "function": { "name": "get_price", "description": "Get a ticker price", "parameters": { "type": "object", "properties": { "symbol": {"type": "string"} }, "required": ["symbol"] } } }], "tool_choice": "auto", }, ) print(r.json())
Starter: standard queue · Standard: higher limits · Extended: priority queue. Exact limits are shown in your account after purchase.