Mercury 2.5

Mercury 2.5 is a reasoning LLM and diffusion LLM (dLLM) from Inception. It is the latest model in the mercury line and is marketed as the fastest reasoning LLM. It has a context window of 260,000 tokens and a maximum output of 65,536 tokens. Pricing starts at $0.04 per million input tokens and $0.15 per million output tokens, with cached input at $0.004 per million. The weights are not open. It supports reasoning mode and tool calling, and accepts and returns text.

Against Mercury Edit 2: window 32K to 260K, input $0.25 to $0.04, output $0.75 to $0.15, cached input $0.025 to $0.004.

Range across the hosts that serve it: up to $0.20 per 1M input tokens.

• ·260k token context window
• ·65k token max output
• ·Reasoning mode and tool calling
• ·Input from $0.04 per million tokens
• ·Cached input at $0.004 per million

• Reach for it for long-context reasoning tasks
• Reach for it for tool-calling workflows
• Reach for it for cost-efficient text generation
• Reach for it for large output generation

5 hosts 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 of Mercury 2.5?

260,000 tokens.

Does Mercury 2.5 support tool calling?

Yes, it supports tool calling and reasoning mode.

What is the pricing for Mercury 2.5?

Input from $0.04 per million tokens, output from $0.15 per million, cached input at $0.004 per million.