DeepSeek-V4.1-Flash vs Mercury 3: Specs & Benchmark Comparison
DeepSeek-V4.1-Flash is developed by DeepSeek, while Mercury 3 comes from Inception. DeepSeek-V4.1-Flash was released in September 2026, and Mercury 3 followed a month later in October 2026. DeepSeek-V4.1-Flash has a published size of about 552 billion parameters; Inception has not disclosed the parameter count of Mercury 3.
We have 26 benchmark results for DeepSeek-V4.1-Flash and 12 benchmark results for Mercury 3, but they overlap on a single test: GPQA Diamond, where DeepSeek-V4.1-Flash scores 90.9% against 89.2%.
Mercury 3 is the cheaper API at $0.10 per million input tokens and $0.35 per million output tokens, roughly 3 times cheaper than DeepSeek-V4.1-Flash at $0.30 and $1.20. Both accept a context window of about 1M tokens. DeepSeek-V4.1-Flash accepts text and images as input, while Mercury 3 accepts text.
| Characteristic | DeepSeek-V4.1-Flash | Mercury 3 |
|---|---|---|
| Company | DeepSeek | Inception |
| Release Date | September 10, 2026 | October 19, 2026 |
| Parameters | 552B | — |
| Multimodal | Yes | No |
| Context (input) | 1.0M | 1.0M |
| Context (output) | 393K | 131K |
| Input Price / 1M | $0.30 | $0.10 |
| Output Price / 1M | $1.20 | $0.35 |
| Average Score | 60.2% | 60.1% |
| Benchmarks | ||
| GPQA Diamond | 90.9% | 89.2% |
Visual Benchmark Comparison
Verdict
Mercury 3 leads in 2 out of 4 comparison categories.
Both models show comparable average scores: DeepSeek-V4.1-Flash — 0.6, Mercury 3 — 0.6.
Mercury 3 is 3.3x cheaper: input $0.10/1M vs $0.30/1M tokens.
Same context size: 1M tokens.
Mercury 3 is newer: released 10/19/2026 vs 9/10/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — DeepSeek-V4.1-Flash or Mercury 3?
Which model is cheaper — DeepSeek-V4.1-Flash or Mercury 3?
Which has a larger context window — DeepSeek-V4.1-Flash or Mercury 3?
The DeepSeek-V4.1-Flash and Mercury 3 comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V4.1-Flash or Mercury 3 page. See also the complete list of AI model comparisons.