Mercury 3
Mercury 3 is Inception's language model with a 1.0M context window and up to 131K output tokens, available from 2 providers, starting at $0.1 / 1M input and $0.35 / 1M output. A diffusion-based language model built for agentic workflows and real-time applications where low latency and tool-use reliability are critical.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $0.1 | $0.35 | $0.01 | |
| $0.1 | $0.35 | $0.01 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Mercury 3 | 1.0M | $0.100 | $0.350 | Current | |
| Mercury 2.5 | 260K | $0.040 | $0.150 | Available | |
| Mercury 2.5 Preview | 260K | — | — | Available | |
| Mercury 2 | 128K | $0.250 | $0.750 | Available | |
| Mercury 2 Edit | — | 32K | $0.250 | $0.750 | Available |
| Mercury Coder Small Beta | 32K | $0.250 | $1.00 | Available | |
| Mercury | — | — | — | — | Available |
| Mercury Coder | — | — | — | — | Available |