How much does Kimi K3.1 Pro cost?

Kimi K3.1 Pro is published as open weights (Kimi K3.1 Pro License (custom; commercial use with restrictions)) — there is no per-token API price. You self-host the model and pay infrastructure cost (GPU rental and operating overhead). Effective cost on commodity 24-48GB GPUs typically lands at $0.10-$0.50 per million output tokens.

What is the context window of Kimi K3.1 Pro?

Kimi K3.1 Pro supports a context window of 1049K tokens (1,048,576 tokens) and can generate up to 33K output tokens per request.

What is Kimi K3.1 Pro best for?

Kimi K3.1 Pro is best for: Best open-weight agentic model if you can host 2.8T. It supports chat, vision, function_calling, code, reasoning capabilities. It is open-source under the Kimi K3.1 Pro License (custom; commercial use with restrictions) license.

Kimi K3.1 Pro

Moonshot AIopen-source NewOpen Source

Moonshot AI's 23 Oct 2026 post-trained refresh of Kimi K3: a 2.8T-total / 104B-active mixture-of-experts model with a 1,048,576-token context window, text and image in, text out, reasoning effort low / high / max (max default). Weights are on Hugging Face under a custom Kimi K3.1 Pro License (commercial use allowed with restrictions). Artificial Analysis Intelligence Index v5.0.1 scores it 46 — the top open-weights model on that index — at $3.68 per Index task, 113M output tokens and 32 tokens/s (slow), with 169.69s to the first answer token. Moonshot's model card reports Terminal-Bench 4.0 65.7, BrowseComp 92.1, HLE-Full with tools 70.0 and GPQA-Diamond 94.2 (vendor-reported), and trails Claude Fable 5.1, GPT-6 Astra and Opus 5.5 on cybersecurity and the hardest reasoning sets. Moonshot's pricing page did not render a readable rate table when checked on 11 Nov 2026, so the token price is not published here and the row shows as self-host; the hosted API (kimi-k3.1-pro, plus a faster kimi-k3.1-pro-highspeed variant) bills batch jobs at 60% of the standard price. Maximum output is not published; the figure shown is Kimi K3's.

Context Window

tokens

Max Output

33K

tokens

Input Price

Self-host

open weights

Output Price

Self-host

infra cost only

Speed

tokens/sec

Released

Oct 2026

2026-10-23

Blended Cost

—

self-host

Value Score

—

n/a self-host

Capabilities

ChatVisionFunction CallingCode GenerationReasoning

Benchmarks

Quality Index

Price vs Quality

Context Window in Context

GPT-5.6 Sol1.1M
GPT-5.6 Terra1.1M
GPT-5.6 Luna1.1M
GPT-6 Astra1.1M
▸ Kimi K3.1 Pro1.0M
Kimi K31.0M
Gemini 4 Carbon1.0M
Gemini 4 Argon1.0M

Bar length is logarithmic — each full step is 10× the tokens. Shown against the models with the nearest context windows, not the directory extremes.

Try in Playground Use via Swfte Connect Moonshot AI Docs

Compare With

Open Source: Licensed under Kimi K3.1 Pro License (custom; commercial use with restrictions)

Not on our gateway yet

Kimi K3.1 Pro is open-weight, so you can run it yourself. Swfte Connect turns your deployment into a managed endpoint that speaks the same API as every other model in this directory.

The request

curl https://api.swfte.com/agents/v2/gateway/chat/completions \
  -H "Authorization: Bearer $SWFTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshot:kimi-k3.1-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Deploy this model with Swfte Connect

About Kimi K3.1 Pro

Kimi K3.1 Pro is a open-source AI model by Moonshot AI, released on October 23, 2026. It supports a context window of 1049K tokens and can generate up to 33K output tokens.

Kimi K3.1 Pro is published as open weights (Kimi K3.1 Pro License (custom; commercial use with restrictions)) for self-hosting. There is no per-token API price. Cost depends on your inference infrastructure: GPU rental, throughput per GPU, and operating overhead. For commodity 24-48GB GPUs the effective cost typically lands in the $0.10-$0.50 per million output tokens range, well below the cheapest hosted alternatives.

Kimi K3.1 Pro is available as an open-source model under the Kimi K3.1 Pro License (custom; commercial use with restrictions) license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.

Using Kimi K3.1 Pro with Swfte

Access Kimi K3.1 Pro through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Kimi K3.1 Pro in our AI Playground before integrating.