One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.25 = $0.25
- Output0.1M x $0.75 = $0.075
$0.325per session
Inception - Closed weights
Mercury Edit 2 pricing and specs
Mercury Edit 2 is a closed-weights model from Inception that costs $0.25 per 1M input tokens and $0.75 per 1M output tokens on the first-party API, with a 32K-token context window.
Last verified from docs.inceptionlabs.ai. All sources
- Input / 1M
- $0.25
- Output / 1M
- $0.75
- Context
- 32K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.25 |
| Output | $0.75 |
| Cache read | $0.025 |
Note: Code-editing dLLM served on v1/fim/completions (autocomplete) and v1/edit/completions (next edit), not chat completions. Docs table states context as 'FIM: 32K, NextEdit: 32K' (recorded as 32000) and max output 8,192; the OpenAPI example model object instead shows context_length 128000 and max_output_length 32000, so the docs table was used and the discrepancy is flagged. The marketing models page says Mercury Edit 2 remains supported for existing customers. Release date is the date on Inception's own blog index for the launch post (the post body does not print a date). Not listed on Vercel AI Gateway (only mercury-2.5, mercury-2 and the older mercury-coder-small appear).
Specs
- Context window
- 32,000 tokens
- Max output
- 8,192 tokens
- Release date
- Provider
- Inception
- API model id
mercury-edit-2- Weights
- Closed weights
What Mercury Edit 2 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.25 = $5.00
- Output5M x $0.75 = $3.75
$8.75per day
$262.50 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.025 = $0.0225
- Uncached input0.1M x $0.25 = $0.025
- Output0.1M x $0.75 = $0.075
$0.1225per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Mercury Edit 2 (this page) | $0.25 | $0.75 |
| Mercury 2Inception | $0.25 | $0.75 |
| Mercury 2.5Inception | $0.20 | $0.75 |
| MiMo-V2.6-ProXiaomi MiMo | $0.435 | $0.87 |
| Codestral 25.08Mistral AI | $0.30 | $0.90 |
Related reading
- Mercury 2 Developer Guide: Building With a Diffusion LLM in ProductionMercury 2 developer guide: the OpenAI-compatible API, tool use, structured outputs, reasoning levels, and when a diffusion LLM beats an autoregressive one.
- Mercury 2: The LLM That Doesn't Generate Like an LLMMercury 2 from Inception Labs is a diffusion reasoning LLM that refines outputs in parallel at over 1,000 tokens per second. How it works and where it fits.
- Diffusion Language Models: How Mercury Changed the LLM Speed GameDiffusion language models like Inception Labs' Mercury draft a whole response and refine it instead of going token by token. See why that makes them so fast.
FAQ
How much does Mercury Edit 2 cost per million tokens?
Mercury Edit 2 costs $0.25 per 1M input tokens and $0.75 per 1M output tokens on Inception's first-party API, per docs.inceptionlabs.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.025.
What is Mercury Edit 2's context window?
Mercury Edit 2 has a 32,000-token context window and returns up to 8,192 output tokens per response.
Are Mercury Edit 2's weights open?
No. Mercury Edit 2 is a closed-weights model. You call it through Inception's API as mercury-edit-2.
When was Mercury Edit 2 released?
Inception released Mercury Edit 2 on March 30, 2026.
Sources
Last verified from docs.inceptionlabs.ai.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.