Inception: Mercury Coder introduces a breakthrough discrete diffusion approach, making it the first dLLM. This innovative architecture allows the model to run 5-10 times faster than even speed-optimized models like Claude 3.5 Haiku and GPT-4o Mini, all while maintaining comparable performance. This unparalleled speed is a game-changer for developers, enabling seamless, in-flow coding experiences with rapid chat-based iteration and highly responsive code completion suggestions. Ranked 1st in speed and tied for 2nd in quality on Copilot Arena, Mercury Coder is designed for efficiency and developer productivity. It supports a context window of 128K tokens and a maximum output of 4K tokens, making it suitable for complex coding tasks. Its capabilities include functions, code generation, and streaming, making it an excellent choice for chat-based development workflows. Access Mercury Coder at the STARTER tier with competitive pricing: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Discover how Mercury Coder can revolutionize your coding workflow today.
✅ Best For
🚀 Capabilities
❌ Limitations
Specifications
| Provider | inception |
| Context Window | 128,000 tokens |
| Max Output | 4,096 tokens |
| Minimum Plan | Balance |
Pricing
| Input Price | $0.2500 / 1M tokens |
| Output Price | $1.0000 / 1M tokens |
💡 With PRO subscription, cost is reduced by 20%