Compare

Claude Fable 5.1 vs Kimi K3

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
Claude Fable 5.1
anthropic/claude-fable-5.1
Kimi K3
moonshot/kimi-k3
Provider
Anthropic
Moonshot
Family
Modality
text
text
Context window
1,000,000 tok
1,048,576 tok
Max output
128,000 tok
32,768 tok
Released
2026-09-01
2026-07-16
License
Proprietary
Open-weight
Input price
$10.00 /1M
$3.00 /1M
Output price
$50.00 /1M
$15.00 /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 →
Claude Fable 5.1
anthropic/claude-fable-5.1
Full spec →

Claude Fable 5.1 is Anthropic's next model in the Fable family, with improvements in agentic coding, long-running agentic workflows, knowledge work, front-end and visual code generation, and finance and analysis tasks. It supports adaptive thinking and a 1M token context window.

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

Compare with another

Gemini 4 Argon vs Kimi K3
google/gemini-4-argon · moonshot/kimi-k3
Claude Sonnet 5.5 vs Kimi K3
anthropic/claude-sonnet-5.5 · moonshot/kimi-k3
Claude Opus 5.5 vs Kimi K3
anthropic/claude-opus-5.5 · moonshot/kimi-k3
GPT-6.1 Sol vs Kimi K3
openai/gpt-6.1-sol · moonshot/kimi-k3
Grok 4.7 vs Kimi K3
xai/grok-4.7 · moonshot/kimi-k3
Kimi K3 vs Glm-5.3
moonshot/kimi-k3 · zai-org/glm-5.3
Kimi K3 vs Qwen3.8-Max
moonshot/kimi-k3 · alibaba/qwen3.8-max
Kimi K3 vs GPT-5.6 Sol
moonshot/kimi-k3 · openai/gpt-5.6-sol
Kimi K3 vs Qwen3.8-27b
moonshot/kimi-k3 · qwen/qwen3.8-27b
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-...",
)

# Claude Fable 5.1
client.chat.completions.create(
    model="anthropic/claude-fable-5.1",
    messages=[{"role":"user","content":"hello"}],
)

# Kimi K3
client.chat.completions.create(
    model="moonshot/kimi-k3",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →