Compare

Kimi K3 vs Gemini 3.6 Flash

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Kimi K3
moonshot/kimi-k3
Gemini 3.6 Flash
google/gemini-3.6-flash
Provider
Moonshot
Google
Family
Gemini 3
Modality
text
text
Context window
1,048,576 tok
1,048,576 tok
Max output
32,768 tok
65,536 tok
Released
2026-07-16
2026-07-21
License
Open-weight
Proprietary
Input price
$3.00 /1M
$1.50 /1M
Output price
$15.00 /1M
$7.50 /1M
Tools
yes
yes
Streaming
yes
yes
Vision
yes
yes
JSON mode
yes
yes
Reasoning
yes
Prompt caching
Batch API
Try it
Open in playground →
Open in playground →
Kimi K3
moonshot/kimi-k3
Full spec →

Kimi K3 is Moonshot's flagship 2.8 trillion-parameter model, built on Kimi Delta Attention (a hybrid linear attention mechanism) with Attention Residuals. It offers native visual understanding, always-on reasoning, and a 1M-token context window for long-horizon coding, knowledge work, and deep reasoning tasks.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Gemini 3.6 Flash
google/gemini-3.6-flash
Full spec →

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost, excelling at code generation, agentic execution, and spatial reasoning.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Claude Opus 5 vs Kimi K3
anthropic/claude-opus-5 · moonshot/kimi-k3
Claude Opus 5 vs Gemini 3.6 Flash
anthropic/claude-opus-5 · google/gemini-3.6-flash
Grok 4.5 vs Kimi K3
xai/grok-4.5 · moonshot/kimi-k3
Grok 4.5 vs Gemini 3.6 Flash
xai/grok-4.5 · google/gemini-3.6-flash
Kimi K3 vs GPT-5.6 Sol
moonshot/kimi-k3 · openai/gpt-5.6-sol
Kimi K3 vs Claude Fable 5
moonshot/kimi-k3 · anthropic/claude-fable-5
Kimi K3 vs DeepSeek V4 Pro
moonshot/kimi-k3 · deepseek/deepseek-v4-pro
Kimi K3 vs Gemini 3.1 Pro
moonshot/kimi-k3 · google/gemini-3.1-pro
Kimi K3 vs MiniMax M3
moonshot/kimi-k3 · minimax/m3
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Kimi K3
client.chat.completions.create(
    model="moonshot/kimi-k3",
    messages=[{"role":"user","content":"hello"}],
)

# Gemini 3.6 Flash
client.chat.completions.create(
    model="google/gemini-3.6-flash",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →