Mercury Edit 2

Mercury Edit 2 is a code editing dLLM from Inception, designed for autocomplete (FIM) and next-edit suggestions. It is part of the mercury line, following Mercury 2. It has a context window of 32000 tokens and a maximum output of 8192 tokens. It accepts and returns text only. It does not support reasoning mode or tool calling. The weights are not open. Pricing starts at $0.25 per million input tokens and $0.75 per million output tokens, with cached input at $0.025 per million tokens. It is served by 1 host.

Against Mercury 2: window 128K to 32K.

• ·Autocomplete (FIM) and next-edit suggestions
• ·32k token context window
• ·8k token max output
• ·Cached input at $0.025 per million tokens

• Reach for it for autocomplete (FIM) in code editors
• Reach for it for next-edit suggestions
• Reach for it for text-to-text code editing tasks

1 host serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 32000 tokens.

What is the pricing?

Input from $0.25 per million tokens, output from $0.75 per million tokens, cached input from $0.025 per million tokens.

Does it support reasoning or tool calling?

No, it does not support reasoning mode or tool calling.