tbuy

kimi-k3 API pricing & access

kimi-k3 API pricing: $2.86 per 1M tokens. kimi-k3. Supports text, image, video input and text output. Listed specifications follow p…

kimi-k3 API access

kimi-k3. Supports text, image, video input and text output. Listed specifications follow public vendor documentation. Available features and limits depend on the selected serving channel.

Compare supported API endpoints and capabilities, then access kimi-k3 through the unified API gateway.

Category
text
Context length
1000000 tokens
Supported APIs
OpenAI Chat Completions API, Anthropic Messages API
API endpoints
POST /v1/chat/completions, POST /v1/messages
Input modalities
text, image, video
Output modalities
text
Capabilities
vision, reasoning, streaming, function calling, structured output, caching

kimi-k3 API pricing

Base input price
$2.86 per 1M tokens
Base output price
$14.29 per 1M tokens

Base prices are shown in USD before group-specific adjustments. Open the live pricing page for current access-group prices.

About kimi-k3

Kimi K3 is a multimodal model from Moonshot AI. Official documentation covers text, image and video understanding, alongside coding and multi-step knowledge work. Evaluate it for screenshot analysis, visually grounded questions, code diagnosis and long-document synthesis.

This site connects to hosted routes through compatible interfaces. Open-weight deployment features do not guarantee that an API route exposes all of them. Check video formats, image handling, tools and reasoning parameters on the selected route. Video understanding and video generation are separate tasks.

Official reference, checked 2026-10-14.

Use cases and prompting

  1. Explain the screenshot context, target area and fields to extract. Require unavailable information to be marked unknown.
  2. Label sources in long material and ask for evidence before conclusions, preserving locations that can be checked.
  3. Validate request formats, results and failures for video or tool workflows on small samples before expanding the task.
  4. Compare text analysis with GLM-5.3 or DeepSeek V4.1 Flash using the same cases. See the API documentation.

How to call kimi-k3

kimi-k3 is served through tbuy's unified gateway. Existing OpenAI or Anthropic SDK code keeps working: point base_url at https://modelsok.com and use your tbuy API key.

curl (OpenAI-compatible)

curl https://modelsok.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "kimi-k3", "messages": [{"role": "user", "content": "Hello"}]}'

Python (openai SDK)

from openai import OpenAI

client = OpenAI(base_url="https://modelsok.com/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Python (anthropic SDK)

from anthropic import Anthropic

client = Anthropic(base_url="https://modelsok.com", api_key="YOUR_API_KEY")
message = client.messages.create(
    model="kimi-k3",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(message.content[0].text)

Frequently asked questions about kimi-k3

What is kimi-k3?

kimi-k3. Supports text, image, video input and text output. Listed specifications follow public vendor documentation. Available features and limits depend on the selected serving channel.

How do I call kimi-k3?

Create an API key with access to kimi-k3, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.

How is kimi-k3 priced?

Pricing depends on the selected provider group and the model billing unit. Refer to the current input, output, request, or media prices in the pricing section.

What is the context window of kimi-k3?

The model catalog lists a context window of 1000000 tokens. Check the selected endpoint for request limits.

How should I evaluate kimi-k3 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.

Back to AI model API pricing