Sophosympatheia: Midnight Miqu 70B v1.5
sophosympatheia/midnight-miqu-70b-v1.5
Access Midnight Miqu 70B v1.5 from Sophosympatheia using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "sophosympatheia/midnight-miqu-70b-v1.5"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "sophosympatheia/midnight-miqu-70b-v1.5"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="sophosympatheia/midnight-miqu-70b-v1.5",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "sophosympatheia/midnight-miqu-70b-v1.5",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Midnight Miqu 70B v1.5 is a 70-billion-parameter roleplay and creative-writing model created by sophosympatheia, an independent model creator, built from the leaked Mistral Medium ("Miqu") 70B weights.
It merges sophosympatheia's earlier Midnight-Miqu-70B-v1.0 with migtissera's Tess-70B-v1.6 using a DARE linear merge, a technique the creator found worked better than SLERP or other approaches tried for this pairing. The result is known for immersive prose, consistent character voice, and handling explicit or complex roleplay scenarios over long exchanges.
On the Open LLM Leaderboard it scores modestly outside its specialty, with 61% on IFEval but under 7% on GPQA and around 2% on MATH Level 5, reflecting a model tuned for storytelling rather than reasoning or knowledge tasks.
The underlying Miqu weights natively support up to 32K context, but through this API context is capped at 18K tokens, a limitation for very long roleplay sessions.
Context Window 18K
tokens
Max Output 18K
tokens
Input Cost $0
per million tokens
Output Cost $0
per million tokens
Release Date N/A
Model Playground
Try Midnight Miqu 70B v1.5 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Midnight Miqu 70B v1.5 by Sophosympatheia through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Midnight Miqu 70B v1.5 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0 |
| Output | $0 |
Midnight Miqu 70B v1.5 supports a context window of 18K tokens. For reference, that is roughly equivalent to 36 pages of text.
Midnight Miqu 70B v1.5 can generate up to 18K tokens in a single response.
Yes — the Midnight Miqu 70B v1.5 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add Midnight Miqu 70B v1.5 to your app without worrying about API keys or setup.
Read the Docs View Tutorials