All models
Inception Labs
Mercury 3 fast
inception/mercury-3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
Input / 1M
$0.10
USD per million tokens
Output / 1M
$0.35
USD per million tokens
Est. cost / token
$0.000000163
$0.16 per 1M, 3:1 mix
Context window
1M
max output 131K
Major features
CachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context5
- agentic3
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.10 | $0.35 | $0.010 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.10
- Output
- $0.35
- Cached input
- $0.010
- Blended (3:1)
- $0.16
Details
- Company
- Inception Labs
- Version
- 3
- Family
- Mercury
- Released
- 2026-10-16
- Parameters
- Undisclosed
- Max output
- 131K
- Open weights
- No
- Inputs
- text
- Last synced
- 25 min ago