inception
Mercury 2.5
Mercury 2.5 is Inception’s diffusion-based reasoning model for chat, agents, and structured workflows, with tool calling, structured outputs, and a 260K context window.
implicit cachingreasoningtool usestructured outputtext
Overview
- Type
- language
- Context
- 260K
- Max output
- 66K
- Input / output
- text / text
API
Model identifier
inception/mercury-2.5Providers and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| inception | Operational | — | — | 100.00% / 100.00% / 99.95% | $0.04/M | $0.15/M | $0.00/M / — | — | — | — | Yes |
Pricing
input
0.00000004
output
0.00000015
input cache read
0.000000004
Capabilities
implicit cachingreasoningtool usestructured outputtext
Supported parameters
max tokens
Yes
temperature
Yes
stop
Yes
tools
Yes
tool choice
Yes
reasoning
Yes
include reasoning
Yes
response format
Yes
structured outputs
Yes
Reasoning options
options
{
"type": "effort",
"values": [
"instant",
"low",
"medium",
"high"
]
}
Metadata
type
language
context window
260K
max output
66K
released
Sep 8, 2026
temperature control
Yes
zero data retention
none
no training
all
api specifications
v2, v3, v4