What the vendor claims, next to what independent boards measured. The two are never mixed in one column.
Source: OpenRouter, as of Oct 28, 09:19 UTC. Model page on OpenRouter
Quoted word for word from the vendor's own launch post or model card. Claims, not measurements.
| Benchmark | Claimed | Source |
|---|---|---|
Output speed (tokens per second)Setting: NVIDIA GPUsThe source says: Speed: 1,068 tokens per second on NVIDIA GPUs. | 1068 | Inception · Oct 19From Drop #035 · Tue, Oct 20 · Morning |
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.
OpenRouter's list price per 1M tokens in each of our snapshots.
Unchanged across our 17 snapshots.
| Snapshot | Input $/1M | Output $/1M |
|---|---|---|
| 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 Oct 28, 09:22 UTC
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.
From Drop #035 · Tue, Oct 20 · Morning