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-2Catalog preview. Paid requests for this model are not enabled yet.
Pricing
~26%USD. No uRouter markup. Live prices can change.
- Input
- $0.183774 / 1,000,000 tokens
- Output
- $0.551321 / 1,000,000 tokens
- Cache read
- $0.018377 / 1,000,000 tokens
- Cache write
- $0.183774 / 1,000,000 tokens
Model details
- Input
- text
- Output
- text
- Context window
- 128,000 tokens
- Maximum output
- 32,768 tokens
- Availability
- Uncapped capacity
- Updated
- 11/8/2026, 1:47:20 AM UTC
Capacity is reserved when your request is accepted.
Price history
Observed best prices · Last 24 hours · UTC
$0.183774/ 1,000,000 tokens
Capabilities
chatstreamingtoolsreasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltystoptoolstool_choiceresponse_formatseedstructured_outputsListed capabilities describe the model. uRouter execution support is verified separately.