Mercury Coder Small
Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.
Model facts
- Context window
- 33K tokens
- Maximum output
- 16K tokens
- Cheapest paid input
- $0.25 per 1M tokens
- Cheapest paid output
- $1 per 1M tokens
- Open weights
- no
- Providers
- 1
Capabilities and modalities
text.
Observed price history
- 2026-08-24: $0.25 input / $1 output per 1M tokens
API providers
- NanoGPT — model id mercury-coder-small; $0.25 input / $1 output per 1M tokens; provider documentation