● Covered by 1 source · 1 reportLow impact1 neutral
Inception's Mercury 2.5 LLM achieves 770 tokens per second output speed
Key points
- Mercury 2.5 achieves 770 tokens per second output speed.
- It has a 260k token context window.
- Pricing is $0.25/1M input tokens and $0.75/1M output tokens.
- The model scores 12 on the Artificial Analysis Intelligence Index.
Model Overview and Performance
Inception released Mercury 2.5, a new large language model. The model supports text input and output, featuring a 260k token context window. It is notable for its speed, achieving an output rate of 770 tokens per second.
Intelligence and Conciseness
Mercury 2.5 scored 12 on the Artificial Analysis Intelligence Index, which is below the median of 13 for comparable models. During evaluation, it generated 35M tokens, demonstrating conciseness compared to the median of 85M tokens.
Pricing Structure
The pricing for Mercury 2.5 is set at $0.25 per 1M input tokens and $0.75 per 1M output tokens. This places it in a moderate price range, with the average cost per task on the Intelligence Index being $0.06.
Release Information
Mercury 2.5 was released on September 8, 2026, and was developed by Inception.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub meta-llama/llama-models GitHub deepseek-ai/DeepSeek-V2 GitHub QwenLM/Qwen GitHub deepseek-ai/deepseek-LLM GitHub deepseek-ai/DeepSeek-Coder-V2 GitHub MiniMax-AI/MiniMax-M2Reporting from
Inception released Mercury 2.5, an LLM that processes text at 770 tokens per second. The model has a 260k token context window and is priced at $0.25 per 1M input tokens and $0.75 per 1M output tokens, positioning it as a moderately priced option with below-average intelligence but high speed.