Moonshot (Kimi)

Source: Kimi API Platform. All model IDs use the prefix moonshot/. Base URL: https://api.moonshot.ai/v1.

Flagship

kimi-k3

Reasoning · Speedmoonshot/kimi-k3Moonshot’s 2.8T-parameter flagship MoE with a 1M-token context window, native vision/video, and always-on reasoning for long-horizon coding and knowledge work. Pass reasoning_effort via model_params (currently "max" only). Do not set temperature — the API fixes it at 1.0.

$3 / $15 (cache-hit input $0.30)
1M context
Text, Image, Video input
Thinking (reasoning_content / reasoning_effort)

Coding

kimi-k2.7-code

Reasoning · Speedmoonshot/kimi-k2.7-codeCoding-focused multimodal model with thinking mode for long-context programming agents.

$0.95 / $4 (cache-hit input $0.19)
256K context
Text, Image, Video input
Thinking

kimi-k2.7-code-highspeed

Reasoning · Speedmoonshot/kimi-k2.7-code-highspeedSame K2.7 Code weights with higher output throughput (~180 tok/s) for interactive coding.

$1.90 / $8 (cache-hit input $0.38)
256K context
Text, Image, Video input
Thinking

General

kimi-k2.6

Reasoning · Speedmoonshot/kimi-k2.6General-purpose multimodal MoE with thinking and non-thinking modes for chat, agents, and vision.

$0.95 / $4 (cache-hit input $0.16)
256K context
Text, Image, Video input
Thinking

kimi-k2.5

Reasoning · Speedmoonshot/kimi-k2.5Previous multimodal MoE generation. Prefer K2.6 or K3 for new workloads. Soft sunset for new users; full sunset August 31, 2026.

$0.60 / $3
256K context
Text, Image input
Thinking

Usage

from timbal import Agent

agent = Agent(
    name="kimi",
    model="moonshot/kimi-k3",
    model_params={"reasoning_effort": "max"},
    tools=[],
)

result = await agent.collect(prompt="Explain Kimi K3 in one sentence.")
print(result.output.collect_text())

Groq OpenAI

​Flagship

kimi-k3

​Coding

kimi-k2.7-code

kimi-k2.7-code-highspeed

​General

kimi-k2.6

kimi-k2.5

​Usage

Flagship

Coding

General

Usage