Mercury 3 is Inception's diffusion LLM, released 2026-10-19. It generates and refines multiple tokens in parallel and, per Inception, runs at more than 1,000 tokens per second on NVIDIA GPUs. 1M token context · up to 131,072 output tokens · text in, text out · reasoning effort instant, low, medium or high · tool calling and structured outputs. List price $0.20 input and $0.70 output per M tokens with cached input 90% off; 50% off at launch ($0.10 and $0.35). Available via the Inception API, Baseten, OpenRouter and Vercel.
No benchmark data available yet.
- Typetext
- Context1.0M tokens (~500 books)
- ReleasedOct 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteJais 3 0.9B · MBZUAIGemma 3 12B (free) · Google DeepMindBenchmarks
Key facts · as of 2026-10-20
- Mercury 3 by Inception. Not enough public benchmark scores to rank yet.
- List price $0.1000 input · $0.35 output per 1M tokens (as of 2026-10-20).
- Sold by 1 provider (as of 2026-10-20): Inception $0.10 in / $0.35 out.
How to cite · data as of 2026-10-20
Mercury 3 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-20. https://benchgecko.ai/model/mercury-3
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP