Aion 3.5 Mini vs Mercury 2: which should you choose in 2026?
Aion 3.5 Mini (by Aion Labs) and Mercury 2 (by Inception) are compared below. Here is how they stack up on benchmarks, price, and capabilities, and which one to pick in 2026.
There are not enough shared, protocol-compatible benchmark results to declare a performance leader.
Mercury 2 is about 2.3× cheaper on a blended 3:1 input/output basis ($0.375 vs $0.875 per 1M tokens).
Aion 3.5 Mini has the larger context window (262,144 tokens vs 128,000 tokens).
Choose Aion 3.5 Mini if…
- • you work with longer documents, transcripts, or codebases
Choose Mercury 2 if…
- • lower blended API cost matters for your workload
The benchmark count includes only results measured with a matching benchmark version and protocol. Arena scores are shown separately. Missing, preliminary, and incompatible data is not treated as a controlled win. Published point-score comparisons are labeled separately when protocol details are incomplete. For text-output models, the verdict also compares token pricing and context windows.
Performance benchmarks
Every value links to its source. A dash means that no reviewed result is available for that exact model and protocol.
| Benchmark | Aion 3.5 Mini | Mercury 2 |
|---|---|---|
A 657-task benchmark of multi-step work across simulated SaaS applications in six business domains. The Artificial Analysis protocol reports a guardrail-aware score and is distinct from both the public Zapier split and the unrelated dynamic AutoBench framework. Guardrail-aware score | — | — |
A benchmark of difficult, verifiable information-seeking questions designed to measure an agent's ability to locate hard-to-find facts through web browsing. Accuracy | — | — |
A verified computer-use benchmark in which multimodal agents operate desktop applications and are graded from the resulting environment state. Mean task reward | — | — |
A human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests. Resolved | — | — |
Version 2.1 of the benchmark for completing realistic tasks in terminal environments. Harness, resource limits, and attempt count are part of the protocol. Mean task success | — | — |
A dynamic LLM evaluation framework in which models generate questions, answer them, and participate in reciprocal peer assessment. AutoBench is distinct from Zapier's AutomationBench. Weighted peer-assessment score | — | — |
The highest-quality subset of Graduate-Level Google-Proof Q&A, designed to test expert-level scientific reasoning in biology, physics, and chemistry. Accuracy | — | — |
A 2,500-question expert-level benchmark spanning dozens of academic fields. Tool-assisted and no-tools results are separate protocols and must not be merged. Accuracy | — | — |
| Arena preference scores | ||
Human preference score | — | 1346 ±11 |
Human preference score for code and web development | — | 1167 ±25 |
Benchmark sources
Reviewed evidence last updated 2026-08-09. Arena data last refreshed Sep 21, 2026.
Pricing, capabilities, and model facts
| Feature | Aion 3.5 Mini | Mercury 2 |
|---|---|---|
| Context & model facts | ||
| Developer | Aion Labs | Inception |
| API provider | AionLabs | Inception |
| Input context | 262,144 tokens | 128,000 tokens |
| Maximum output | 32,768 tokens | 50,000 tokens |
| Released | — | — |
| Added to Writingmate | Sep 23, 2026 | Mar 4, 2026 |
| License | Not available | Not available |
| Knowledge cutoff | — | — |
| Capabilities | ||
| Inputs | Text | Text |
| Outputs | Text | Text |
| Provider endpoint accepts tool parameters | Yes | Yes |
| Reasoning | Yes | Yes |
| Vision | No | No |
| Image Generation | No | No |
| Video Generation | No | No |
| API pricing | ||
| Input (per 1M tokens) | $0.70 | $0.25 |
| Output (per 1M tokens) | $1.40 | $0.75 |
| Blended 3:1 input/output | $0.875 | $0.375 |
| API performance | ||
| p95 latency | Not measured | Not measured |
| Output throughput | Not measured | Not measured |
| Writingmate shows API performance only when both models have enough observations from the same measurement window, prompt profile, and provider. Third-party latency values are not copied into this table. | ||
Data sources
- Writingmate model catalog (pricing, limits, and availability)
Catalog data last updated Sep 23, 2026.
Why Pay for Multiple Subscriptions?
Comparing Aion 3.5 Mini from Aion Labs with Mercury 2 from Inception? Instead of managing separate API keys and subscriptions, get both with Writingmate.
| Plan | Price | Aion 3.5 Mini | Mercury 2 | AI Images | AI Video |
|---|---|---|---|---|---|
Writingmate Pro Most popular | $20/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Writingmate Ultimate Power users | $60/mo | Included | Included | Nano Banana Pro, FLUX.2, DALL-E & more | Sora 2, VEO 3.1 |
Aion 3.5 Mini vs Mercury 2 FAQ
Which is better, Aion 3.5 Mini or Mercury 2?
There are not enough shared, protocol-compatible benchmark results to declare a performance leader. Mercury 2 is about 2.3× cheaper on a blended 3:1 input/output basis ($0.375 vs $0.875 per 1M tokens). Aion 3.5 Mini has the larger context window (262,144 tokens vs 128,000 tokens).
Which model is cheaper to use through an API?
Mercury 2 is about 2.3× cheaper on a blended 3:1 input/output basis ($0.375 vs $0.875 per 1M tokens).
Which model supports more context?
Aion 3.5 Mini has the larger context window (262,144 tokens vs 128,000 tokens).
Can I switch between Aion 3.5 Mini and Mercury 2?
Yes. Use the model selector on this page to open any current Writingmate model comparison. You can also run the same prompt with both models in Writingmate.
Related comparisons
More Aion 3.5 Mini comparisons
Ember-1
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3.
GLM 5.3 Prime
Z.AI
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration.
Qwen3.8 Max Prime
Qwen
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point.
Space Bunny Alpha
Stealth
Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support.
Solar Mini 4
Upstage
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window.
Command A+
Cohere
Command A+ is Cohere's flagship model for enterprise agentic workflows.
More Mercury 2 comparisons
Ember-1
Fireworks
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3.
GLM 5.3 Prime
Z.AI
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration.
Qwen3.8 Max Prime
Qwen
Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point.
Space Bunny Alpha
Stealth
Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support.
Aion 3.5
Aion Labs
Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
Solar Mini 4
Upstage
Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window.