Models · Long context
Mercury 3
by Inception
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date.
Our verdict
We have not reviewed Mercury 3 yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Mercury 3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date.
Notes
Mercury 3 is listed in the EDNA Models directory from the OpenRouter catalogue.
Key facts
What we have checked
- Input price
- $0.100 per million tokens
- Output price
- $0.350 per million tokens
- Price on inception
- $0.010 per million cached input tokens
- Price on inception
- $0.100 per million input tokens
- Price on inception
- $0.350 per million output tokens
- Latest version
- inception/mercury-3-20261019
- Time to first token (ms) on inception
- 1,087
- Output speed (tokens a second) on inception
- 307
- Tokens served on OpenRouter in a day
- 9.5B (for 31 Oct 2026)
- Tool calls on OpenRouter in a day
- 79.1K (for 31 Oct 2026)
- Design Arena rating (Elo)
- 1,232
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
API access
How to call it
Call via OpenRouter with model id `inception/mercury-3`.
- openrouter ·
inception/mercury-3· Docs
OpenRouter id: inception/mercury-3
Price
What Mercury 3 costs, over time
$0.100 to $0.100
$0.350 to $0.350
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| inceptionCached input | $0.010 per million cached input tokensSince 27 Oct 2026 | No change recorded | OpenRouter models API |
| inceptionInput | $0.100 per million input tokensSince 27 Oct 2026 | No change recorded | OpenRouter models API |
| inceptionOutput | $0.350 per million output tokensSince 27 Oct 2026 | No change recorded | OpenRouter models API |
Usage
How much Mercury 3 is used
19.3B to 9.5B
Scores
How Mercury 3 scores
Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.
| Score | Value | Source | Checked |
|---|---|---|---|
| Design Arena rating (Elo) | 1,232EloAs of 31 Oct 2026 | Design Arena via OpenRouter |
Sources
Where this comes from
- OpenRouter models APIRegistry
- OpenRouter models APIThird party
- OpenRouter models APIOfficial
- Design Arena via OpenRouterThird party
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
USAGE / OPENROUTER
How much Mercury 3 is used
Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.
- Tokens, last 7 days
- 89.4B
- Requests, last 7 days
- 3.2M
- Tool calls, last 7 days
- 894K
- Average cost per request
- 14.8¢
- Price per million tokens
- $0.1 in · $0.35 out
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Mercury 3.
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-10-26. Hosting routes and app features can differ.
inception/mercury-3- Tool calling
- Listed support
- Structured output
- Listed support
- Reasoning controls
- Listed support
- Availability
- available
- Price basis
- token
- Licence verification
- Check the developer licence; the model name is insufficient
- Context length
- 1M tokens
- Knowledge cutoff
- Not established
- Developer release date
- Not established
- First seen in the catalogue
- 16 Oct 2026
- Listed retirement date
- Not established
Inspect the sources and their scope
inception/mercury-3: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-10-26Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.
Checked 2026-10-26FROM SPECIFICATIONS TO YOUR WORK
Is this the right model for your job?
Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.
What would it cost?
Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.
Enter a whole number of runs from 1 to 100,000,000.
Working out the cost...
Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗
Check the source
Price date: 31 Oct 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.
Model source & availability ↗Understand the evidence
Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.
Vals Index: 43.659 (2026-10-30) ↗Design Arena: 1232 (2026-10-30) ↗Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.