Long-context reasoning model with multimodal input and adjustable reasoning
One unified API for accessing 1000+ AI models across image, video, audio, and language generation
Stage
Not given
Not given
Founded
Not given
2023
Based in
Not given
US
Pricing model
Paid
Paid
Pricing
Starter: $9.9 for 100,000 permanent credits; Pro: $99 for 1,000,000 permanent credits; Enterprise: $999 for 11,000,000 permanent credits (includes 10% extra). One-time purchase, no subscription, credits never expire.
Usage-based pricing per API call. Models are priced individually with pay-per-use billing; prices vary by model and modality. Customers can set a budget and see what it purchases across all model categories.
Key features
1 million token context window
Text, image and video input support
Five adjustable reasoning levels
Tool calling and function execution
JSON output format support
OpenAI-compatible API
Online playground for prompt evaluation
Maximum 524,288 completion tokens
Server-side API key management
Streaming and structured responses
Video generation from text or images with Kling and MiniMax models
Managed agents with autonomous AI assistants
Webhook support for async task completion notifications
WebSocket real-time task tracking and status updates
n8n workflow integration for no-code automation
What makes it different
One million token context window for handling long documents and entire codebases without fragmentation
Adjustable reasoning effort allows matching speed and depth to specific task requirements
Multimodal input combining text, images and video in a single conversation
Independent service with anonymous model developer and transparent limitations
Built-in tool calling keeps application control over permissions and side effects
Single unified API replacing multiple provider integrations
Transparent pay-per-use pricing with clear cost visibility
No subscription required, pay only for completed successful tasks
Quick integration enabling production features in days rather than months
Production-ready infrastructure with autoscaling and low latency