Inkling vs Mercury 3
Inkling and Mercury 3 are closely matched at 37.1 and 36.1 on the LLM Stats Score. Mercury 3 is 10.6x cheaper per token.
Thinking Machines Lab · Inception · Updated for 2026
Which is better?
Inkling and Mercury 3 are closely matched on the overall LLM Stats Score at 37.1 and 36.1.
In the 3 individual benchmarks reported for both models, Inkling wins 2; this is a narrower head-to-head signal than the composite indexes.
On price, Mercury 3 is roughly 10.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Mercury 3 also accepts a larger context window (1,000,000 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Inkling
- you value its reported benchmark strengths — it wins 2 of 3 exact shared results
- you need open weights you can self-host or fine-tune
Choose Mercury 3
- cost matters — it's about 10.6x cheaper per token
- you process long inputs — it offers a 1,000,000 token context window
- you want the most recent training data — it shipped Oct 2026
At a glance
The differences that matter most.
Individual benchmarks
16 reported for Inkling · 12 for Mercury 3
Inkling outperforms in 2 benchmarks (GDPval-AA, IFBench), while Mercury 3 is better at 1 benchmark (Tau3 Banking).
Inkling shows notably better performance in the majority of benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Inkling ($0.95/1M tokens) is 9.5x more expensive than Mercury 3 ($0.10/1M tokens).
For output processing, Inkling ($4.05/1M tokens) is 11.6x more expensive than Mercury 3 ($0.35/1M tokens).
In conclusion, Inkling is more expensive than Mercury 3.*
* Using a 3:1 ratio of input to output tokens
Context Window
Maximum input and output token capacity
Mercury 3 accepts 1,000,000 input tokens compared to Inkling's 524,288 tokens. Inkling can generate longer responses up to 524,288 tokens, while Mercury 3 is limited to 131,072 tokens.
Input capabilities
Documented input modalities across available providers
Inkling supports multimodal inputs, whereas Mercury 3 does not.
Inkling can handle both text and other forms of data like images, making it suitable for multimodal applications.
Inkling
Mercury 3
License
Usage and distribution terms
Inkling is licensed under Apache 2.0, while Mercury 3 uses a proprietary license.
License differences may affect how you can use these models in commercial or open-source projects.
Apache 2.0
Open weights
Proprietary
Closed source
Release Timeline
When each model was launched
Inkling was released on 2026-07-21, while Mercury 3 was released on 2026-10-19.
Mercury 3 is 3 months newer than Inkling.
Jul 21, 2026
3 months ago
Oct 19, 2026
3 days ago
3mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
Inkling is available from DeepInfra. Mercury 3 is available from Inception.
Inkling
Mercury 3
Outputs Comparison
Judge for yourself.
Run your own prompts against Inkling and Mercury 3 side-by-side, then vote on the output you prefer.
FAQ
Common questions about Inkling vs Mercury 3.