Mercury 2
Mercury 2 is a language model. It is currently free at 1 provider with up to 128K tokens of context.
- Context
- 128K tokens
- Type
- Text
- License
- Proprietary
- Free since
- September 20, 2026
Where to use Mercury 2 for free
Each row is a separate free endpoint with its own limits.
Quick start
curl https://api.unorouter.com/v1/chat/completions \
-H "Authorization: Bearer $UNOROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mercury-2:free",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.unorouter.com/v1",
api_key="YOUR_UNOROUTER_API_KEY",
)
reply = client.chat.completions.create(
model="mercury-2:free",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.unorouter.com/v1",
apiKey: process.env.UNOROUTER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "mercury-2:free",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(reply.choices[0].message.content);Example for UnoRouter. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.
Benchmarks
Source: Artificial Analysis · Mercury 2
Similar free models
FAQ
Is Mercury 2 free?
Yes. As of November 2, 2026, Mercury 2 is free at UnoRouter. Each provider has its own limits — see the table above.
What is the context window of Mercury 2?
The largest context among free routes is 128,000 tokens. Some providers cap it lower.
How do I call Mercury 2 via API?
Use any OpenAI-compatible client with base URL https://api.unorouter.com/v1, model ID mercury-2:free, and a UnoRouter key.
How good is Mercury 2?
Artificial Analysis Intelligence Index: 13.8, GPQA Diamond: 77%. For comparison, the strongest free model in the catalog right now is GLM 5.3 Flash.
Is Mercury 2 open-weight?
No, it is proprietary: access is only through provider APIs.