Inception Labs
Mercury 2
Mercury 2 — diffusion-based reasoning LLM from Inception, delivering high-speed generation with strong reasoning, tool use, and structured output.
mercury-2Pricing
~40%- Input
- $0.15 / 1,000,000 tokens
- Output
- $0.45 / 1,000,000 tokens
- Cache read
- $0.015 / 1,000,000 tokens
- Cache write
- $0.15 / 1,000,000 tokens
Discount history
Model details
- Input
- text
- Output
- text
- Context window
- 128,000 tokens
- Maximum output
- 32,768 tokens
- Availability
- Uncapped capacity
- Updated
- 11/8/2026, 3:58:06 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingReasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltystoptoolstool_choiceresponse_formatseedstructured_outputs