DeepInfra raises $107M Series B to scale the inference cloud — read the announcement
Kimi Model Family
Kimi is Moonshot AI's family of open-weight large language models, built on a sparse mixture-of-experts architecture that activates only a fraction of its parameters per token — frontier-class quality at a cost open models can sustain. The family spans general chat, deep reasoning, multimodal, and code-focused variants, all designed for the workloads that break lighter models: long-context understanding over large documents and codebases, reliable structured output and function calling, and multi-step agentic workflows.
Featured Model: moonshotai/Kimi-K3
Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. Its architecture relies on KDA and Attention Residuals for computational efficiency.
Price per 1M input tokens
$2.85
Price per 1M cached input tokens
$0.285
Price per 1M output tokens
$14.25
Release Date
07/27/2026
Context Size
1,048,576
# Assume openai>=1.0.0
from openai import OpenAI
# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
api_key="$DEEPINFRA_TOKEN",
base_url="https://api.deepinfra.com/v1/openai",
)
chat_completion = openai.chat.completions.create(
model="moonshotai/Kimi-K3",
messages=[{"role": "user", "content": "Hello"}],
)
print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)
# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
Featured Model: moonshotai/Kimi-K2.7-Code
Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.
Price per 1M input tokens
$0.68
Price per 1M cached input tokens
$0.136
Price per 1M output tokens
$3.40
Release Date
06/15/2026
Context Size
262,144
Quantization
fp4
# Assume openai>=1.0.0
from openai import OpenAI
# Create an OpenAI client with your deepinfra token and endpoint
openai = OpenAI(
api_key="$DEEPINFRA_TOKEN",
base_url="https://api.deepinfra.com/v1/openai",
)
chat_completion = openai.chat.completions.create(
model="moonshotai/Kimi-K2.7-Code",
messages=[{"role": "user", "content": "Hello"}],
)
print(chat_completion.choices[0].message.content)
print(chat_completion.usage.prompt_tokens, chat_completion.usage.completion_tokens)
# Hello! It's nice to meet you. Is there something I can help you with, or would you like to chat?
# 11 25
Available Kimi Models
Kimi is Moonshot AI's family of multimodal language models optimized for long-context understanding, agentic workflows, and high-throughput inference.
FAQ
How do I integrate Kimi models into my application?
What are the pricing details for using Kimi models on DeepInfra?
- Input Tokens: between $0.45 and $2.85 per million
- Output Tokens: between $2.25 and $14.25 per million
How do I get started using Kimi on DeepInfra?
- Get your API key
- Test models directly from the browser, cURL, or SDKs
- Review pricing on your usage dashboard
© 2026 DeepInfra. All rights reserved.