Inception: Mercury 2
by InceptionInception: Mercury 2 is a large language model from Inception. It costs $0.250 per million input tokens and $0.750 per million output tokens. Its context window is 128K tokens.
- Input / 1M tokens
- $0.250
- Output / 1M tokens
- $0.750
- Cached input / 1M
- $0.025
- Context window
- 128K
On repeated prefixes
tokens
Who serves it cheapest
1 hosts serve Mercury 2. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| InceptionCheapest | $0.250 | $0.750 | 128K | - | 100.0% |
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 11.5
- Coding index
- 31.1
- Agentic index
- 4.0
About Mercury 2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
Specifications
| Model ID | inception/mercury-2 |
|---|---|
| Provider | Inception |
| Context window | 128K tokens |
| Max output | 50K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | March 4, 2026 |
Cheaper alternatives
Models that cost less than Mercury 2 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Inception: Mercury 2 cost?
$0.250 per million input tokens and $0.750 per million output tokens. Cached input reads cost $0.025 per million tokens.
What is the context window of Inception: Mercury 2?
128K tokens, with up to 50K tokens of output per request.