Mercury 3 is a specialized chat model built by Inception to handle complex text based tasks. It is designed to provide high quality reasoning and reliable outputs for various applications.
The model architecture supports streaming responses and structured data formats. It integrates seamlessly with external tools to enhance its functional capabilities.
The model is built to handle complex logical tasks and provide coherent responses.
Generate data in specific formats to ensure compatibility with your existing systems.
Connect the model to external tools to expand its operational reach.
Receive model outputs in real time as they are generated.
Automate complex reasoning tasks for data analysis.
Generate structured text outputs for software integration.
Build interactive chat applications with tool support.
Process long form text documents with a large context window.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "inception/mercury-3", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "inception/mercury-3", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"inception/mercury-3","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Billed per token: $0.27508 / 1M input tokens, $0.027508 / 1M cached input tokens and $0.96278 / 1M output tokens. Reasoning tokens are billed as output.
Automate complex reasoning tasks for data analysis.
Generate structured text outputs for software integration.
Build interactive chat applications with tool support.
Process long form text documents with a large context window.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Mercury 3 This page | Complex reasoning and structured text generation | |||
| Low-latency reasoning and agent loops | ||||
| Agentic workflows and structured output | ||||
| Coding and long-horizon agentic workflows | ||||
| High-volume, low-latency tasks |
Mercury 3 costs $0.27508 / 1M tokens for input and $0.96278 / 1M tokens for output on AI/ML API. Cached input is billed at $0.027508 / 1M tokens.
Mercury 3 was developed by Inception.
The model supports text to text generation.
The model supports a context window of 1,000,000 tokens.
Yes, Mercury 3 supports tool integration.
