Mercury 2
Mercury 2 is Inception's language model with a 128K context window and up to 50K output tokens, available from 2 providers, starting at $0.250 / 1M input and $0.750 / 1M output. A fast reasoning diffusion LLM from Inception Labs that produces and refines multiple tokens in parallel, combining reasoning capability with diffusion-based speed.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 OpenRouter | $0.250 | $0.750 | $0.025 |
 Vercel AI Gateway | $0.250 | $0.750 | $0.025 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Mercury 2 | 128K | $0.250 | $0.750 | Current | |
| Mercury Coder Small Beta | 32K | $0.250 | $1.00 | Available | |
| Mercury | — | — | — | — | Available |
| Mercury Coder | — | — | — | — | Available |