Dots Studio: Dots3-Note Preview (free) vs Free Models Router
A side-by-side comparison of Dots Studio: Dots3-Note Preview (free) (Free) and Free Models Router (Free) using current USD prices and capabilities from the api14 catalog. Both run through the same OpenAI-compatible API.
Specifications
| Dots Studio: Dots3-Note Preview (free) | Free Models Router | |
|---|---|---|
| Provider | Dots Studio | OpenRouter |
| Context window | 512,000 | 200,000 |
| Max output | 460,800 | - |
| Input | text, image | text, image |
| Output | text | text |
| Tool calling | ||
| Structured output | ||
| Reasoning control | ||
| Added | Aug 14, 2026 | Feb 1, 2026 |
Key differences
- Dots Studio: Dots3-Note Preview (free) reads 2.6× more context (512,000 tokens).
In depth
Dots Studio: Dots3-Note Preview (free) is a text model from Dots Studio, released on 2026-08-14. Free Models Router is a text model from OpenRouter, released on 2026-02-01. Both are served through api14 as OpenAI-compatible endpoints, and both take text and image input while returning text output, so at the level of basic shape they look similar. The differences show up in context size and in the tuning parameters each one exposes.
The clearest split is context length. Dots3-Note Preview offers 512000 tokens of context, while Free Models Router offers 200000. That makes Dots3-Note Preview the one with the bigger context window, which matters if you are feeding long documents, large codebases or extended conversation histories in a single call. On modalities the two are the same: text and image in, text out. The qualitative comparison does not mark either model as the only one supporting tools, structured outputs or reasoning, so treat those as available on both rather than as a way to choose. Where they do diverge is parameter surface. Free Models Router exposes a wider set of sampling and decoding controls, including frequency_penalty, presence_penalty, repetition_penalty, min_p, top_k, seed, stop, logprobs and top_logprobs, plus reasoning_effort. Dots3-Note Preview covers the common set (temperature, top_p, max_tokens, tools, tool_choice, response_format, structured_outputs, reasoning, include_reasoning) but not the extra knobs.
For practical selection, start with the context requirement. If your prompt plus expected output can exceed roughly 200000 tokens, Free Models Router is not the right call and Dots3-Note Preview is. If you are working well inside that budget, the decision comes down to control. Free Models Router gives you deterministic sampling via seed, token-level log probabilities, and finer penalties, which helps when you are debugging model behaviour, running evaluations, or need reproducible outputs across runs. Dots3-Note Preview is the simpler target when you just want a large-context call with the standard OpenAI-style parameters and do not need logprobs or seed control. Neither model is flagged as cheaper or more expensive than the other in the qualitative data, so cost is not a deciding factor here; check the live price table on the page for current rates.
Calling either model through api14 works the same way. Both are OpenAI-compatible, so you point your client at the api14 base URL, send a chat completions request with your messages, and set the model field. To use Dots3-Note Preview, set the model id to "dots-studio/dots-3-note-preview:free". To use Free Models Router, set it to "openrouter/free". Everything else in the request body stays the same, which means you can switch between them by changing one string, or route between them at runtime based on prompt length or whether you need seed and logprobs.
There is a case where Free Models Router remains the better pick even though Dots3-Note Preview has the larger window. If your task fits inside 200000 tokens and you depend on reproducible sampling, token log probabilities for scoring or debugging, or the extra penalty and top_k controls, Free Models Router is the more suitable endpoint. The larger context of Dots3-Note Preview does not compensate for missing those parameters, so match the model to the constraint that actually binds your workload.
Switch with one string
Both models use the same endpoint and request shape. Change the model value from "dots-studio/dots-3-note-preview:free" to "openrouter/free" and prompts, streaming and tools keep working.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "openrouter/free",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
More comparisons
- LiquidAI: LFM3-1.7B vs Ricursive: Ripple 65B Preview
- LiquidAI: LFM3-1.7B vs Crouton Alpha
- LiquidAI: LFM3-1.7B vs Tencent: Hy4
- LiquidAI: LFM3-1.7B vs Z.ai: GLM 5.3 FlashX Legal
- Ricursive: Ripple 65B Preview vs Crouton Alpha
- Ricursive: Ripple 65B Preview vs Tencent: Hy4
- Ricursive: Ripple 65B Preview vs Z.ai: GLM 5.3 FlashX Legal
- Crouton Alpha vs Tencent: Hy4