Inception · LLMs & Coding
Mercury 2
Catalog data · checked Nov 16, 2026
Mercury 2 is a language model from Inception, released in February 2026. It reads text and writes text, with a context window of 128K tokens and up to 50K output tokens per answer. It costs $0.25 per million input tokens and $0.75 per million output tokens. That makes it cheaper than 76% of the 185 paid language models we track.
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
More prices
| Cached input (read) | $0.025 /1M |
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $0.388 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | too long |
| 10,000 product descriptions300 input and 200 output tokens per text | $2.25 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $0.863 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare Mercury 2 with
Questions & answers
How much does Mercury 2 cost?
Mercury 2 costs $0.25 per 1 million input tokens and $0.75 per 1 million output tokens (USD, list price checked Nov 16, 2026).
How large is the context window of Mercury 2?
Mercury 2 can process up to 128,000 tokens per request and return up to 50,000 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does Mercury 2 support tool calling?
Yes. The API accepts tool (function) definitions and also supports structured JSON output.
Can Mercury 2 read images?
No, this model accepts text only.
