Mercury 2
Inception · inception/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...
Mercury 2 ranks #141 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.50 blended per million tokens, it is cheaper than 69% of models with published API pricing. Its 128,000-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 50000
Pricing
Output / 1M: 0.75
Blend / 1M: 0.50
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.50per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.50 |
| 10,000,000 | $5.00 |
| 100,000,000 | $50.00 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Inception
- Mercury 2.5 Preview$0.10 / 1M
Closest API price
- ReMM SLERP 13B$0.50 / 1M
- Qwen3.6 35B A3B$0.50 / 1M
- GLM 4.5 Air$0.49 / 1M
- Qwen Plus 0728$0.52 / 1M
- Qwen-Plus$0.52 / 1M