Wirestack
Together AI serves Kimi K3.1 Pro with a 1M-token context at $2 input and $10 output (November 5, 2026)
Kimi K3.1 Pro is now a Together AI serverless model: 1M-token context, image input, tools, $2 in and $10 out per 1M tokens.
Your keys
0 of 1 ready
Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
- Together AI API keyTOGETHER_API_KEYGet key
Select Create key on your project's API keys page. The key is shown only once.
3 of 3 free copies left this month.Unlimited with Pro
What you get
On November 5, 2026 Together AI added Kimi K3.1 Pro to its serverless models, as moonshotai/Kimi-K3.1-Pro.
- Context length: 1,048,576 tokens.
- Takes text and image input. Supports function calling and structured outputs.
- Runs in NVFP4 quantization.
- Price per 1M tokens: $2.00 input, $10.00 output, $0.20 cached input.
A day earlier, on November 4, the same model became available for post-training with LoRA on B200-SXM. Training context is 163,840 tokens, LoRA rank goes up to 32, and adapters can't be deployed on dedicated model inference yet.
Prerequisites
Steps
- Set your key:
- Send a chat completion. This is the quickstart example with the model string changed to Kimi K3.1 Pro:
from together import Together
client = Together() # reads TOGETHER_API_KEY from environment
response = client.chat.completions.create(
model="moonshotai/Kimi-K3.1-Pro",
messages=[
{
"role": "user",
"content": "What are the top 3 things to do in New York?",
}
],
)
print(response.choices[0].message.content)