Long-context reasoning model with multimodal input and adjustable reasoning
Stage
Startup
Not given
Founded
2024
Not given
Based in
US
Not given
Pricing model
Paid
Paid
Pricing
Pay-as-you-go pricing for serverless inference charged per token and for on-demand deployments charged per GPU usage time. New users receive free credits. Text models range from $0.05 to $1.5 per 1M tokens (input and output), including Llama-3.2-1B-Instruct at $0.06/1M tokens, Meta-Llama-3.1-8B-Inst
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.
Key features
Text generation with multiple LLM models including Llama, Qwen, and DeepSeek
Embedding and reranking models for RAG applications
Text-to-image and text-to-video generation
Voice generation with ASR/TTS models
Single line of code integration
Agent application with ultra-low latency
Chat2DB application with real-time responsiveness
Inference acceleration capability
Competitive pricing with reduced costs
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
What makes it different
Out-of-the-box inference acceleration capability
Fast model updates and comprehensive model selection
Single line of code integration with no deployment complexity
Ultra-low latency for responsive applications
Free credits for new users to get started
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
Space Bunny