Mercury 3
Inception · 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...
Mercury 3 ranks #76 of 377 models in the default AI Benchmark Hub order (quality first, then cost). At $0.22 blended per million tokens, it is cheaper than 79% of models with published API pricing. Its 1,000,000-token context window is 3.8× the catalog median (262,144 tokens).
texttext->text
Context
Max context: 1000000
Max output: 131072
Max output: 131072
Pricing
Input / 1M: 0.10
Output / 1M: 0.35
Blend / 1M: 0.22
Output / 1M: 0.35
Blend / 1M: 0.22
Quality
Quality index: —
Provider
Provider: Inception
Moderated: no
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.22per 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 | $0.22 |
| 10,000,000 | $2.25 |
| 100,000,000 | $22.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Inception
- Mercury 2.5$0.10 / 1M
- Mercury 2$0.50 / 1M
Closest API price
- GPT-5 Nano$0.22 / 1M
- GLM 4.7 Flash$0.23 / 1M
- Gemma 3 27B$0.21 / 1M
- DeepSeek Flash Latest$0.21 / 1M
- MiMo-V2.6-Flash$0.21 / 1M