Measured by independent sources (Epoch AI, LMArena, OpenRouter's benchmark runs, τ²-bench, Vectara), not by the vendor. "Listed as" is the source's own name for the model, so you can check our match.
No independent results yet. They appear here as Epoch AI and LMArena add this model.
Price history
OpenRouter's list price per 1M tokens in each of our snapshots.
$0.4$0
Oct 20, 2026Nov 8, 2026
Output now $0.35
Input now $0.1
Unchanged across our 39 snapshots.
Show the numbers
This model's OpenRouter price in each of our snapshots
Snapshot
Input $/1M
Output $/1M
Nov 8, 04:03 UTC
$0.1
$0.35
Nov 7, 16:04 UTC
$0.1
$0.35
Nov 7, 04:04 UTC
$0.1
$0.35
Nov 6, 16:04 UTC
$0.1
$0.35
Nov 6, 04:04 UTC
$0.1
$0.35
Nov 5, 16:05 UTC
$0.1
$0.35
Nov 5, 10:05 UTC
$0.1
$0.35
Nov 4, 16:02 UTC
$0.1
$0.35
Nov 4, 04:04 UTC
$0.1
$0.35
Nov 3, 16:04 UTC
$0.1
$0.35
Nov 3, 13:26 UTC
$0.1
$0.35
Nov 2, 16:01 UTC
$0.1
$0.35
Nov 2, 04:04 UTC
$0.1
$0.35
Nov 1, 16:03 UTC
$0.1
$0.35
Nov 1, 04:04 UTC
$0.1
$0.35
Oct 31, 16:04 UTC
$0.1
$0.35
Oct 31, 04:04 UTC
$0.1
$0.35
Oct 30, 16:03 UTC
$0.1
$0.35
Oct 30, 04:04 UTC
$0.1
$0.35
Oct 29, 16:03 UTC
$0.1
$0.35
Oct 29, 04:04 UTC
$0.1
$0.35
Oct 28, 16:04 UTC
$0.1
$0.35
Oct 28, 09:22 UTC
$0.1
$0.35
Oct 27, 16:03 UTC
$0.1
$0.35
Oct 27, 04:03 UTC
$0.1
$0.35
Oct 26, 16:04 UTC
$0.1
$0.35
Oct 26, 04:03 UTC
$0.1
$0.35
Oct 25, 16:04 UTC
$0.1
$0.35
Oct 25, 06:03 UTC
$0.1
$0.35
Oct 24, 15:04 UTC
$0.1
$0.35
Oct 24, 03:03 UTC
$0.1
$0.35
Oct 23, 15:03 UTC
$0.1
$0.35
Oct 23, 03:04 UTC
$0.1
$0.35
Oct 22, 15:03 UTC
$0.1
$0.35
Oct 22, 05:04 UTC
$0.1
$0.35
Oct 21, 15:03 UTC
$0.1
$0.35
Oct 21, 03:02 UTC
$0.1
$0.35
Oct 20, 15:04 UTC
$0.1
$0.35
Oct 20, 03:03 UTC
$0.1
$0.35
Source: OpenRouter, as of Nov 8, 04:03 UTC
In the Drops
ModelsNEW
Inception's Mercury 3 diffusion LLM claims 1,068 tokens per second
Inception says Mercury 3 beats GPT-6 Luna and Claude Haiku 5.5 across a range of benchmarks while running 4–8x faster, with a 1M-token context. Launch price is $0.10 per 1M input, $0.35 output.
Why it matters: It's on OpenRouter, Baseten and Vercel and is OpenAI API compatible: a fast, cheap option for latency-bound agents. The quality claims are Inception's own.