Compare

Claude Fable 5 vs Kimi-K2.6

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
anthropic/claude-fable-5
Kimi-K2.6
moonshot/kimi-k2.6
Provider
Anthropic
Moonshot
Family
Kimi
Modality
text
text
Context window
1,000,000 tok
262,144 tok
Max output
128,000 tok
16,384 tok
Released
2026-06-09
2026-04-20
License
Proprietary
Open-weight
Input price
$10.00 /1M
$0.950 /1M
Output price
$50.00 /1M
$4.00 /1M
Cache read
$0.160 /1M
Tools
yes
yes
Streaming
yes
yes
Vision
yes
yes
JSON mode
yes
yes
Reasoning
yes
Prompt caching
yes
Batch API
Try it
Open in playground →
Open in playground →
Claude Fable 5
anthropic/claude-fable-5
Full spec →

Claude Fable 5 is Anthropic's most capable widely released model, built for the most demanding reasoning and long-horizon agentic work. Adaptive thinking is always on, and the model supports a 1M token context window with up to 128k output tokens per request.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Kimi-K2.6
moonshot/kimi-k2.6
Full spec →

Kimi K2.6 is a frontier-scale open-source 1T parameter model with a 262.1k context window, multi-turn tool calling, vision inputs, and structured outputs for agentic workloads.

Strengths
  • Frontier-scale 1T parameters, open-weight
  • ~10× cheaper than Opus
  • Multi-turn tool calling + vision
Use cases
Code agentsLong-document reasoningCost-conscious production

Benchmarks

Claude Fable 5
Kimi-K2.6
HumanEval
92.7
SWE-Bench
68.2

Source: each provider's published benchmarks. Higher is better. Run an eval to compare on your own data.

Compare with another

Kimi-K2.6 vs Claude Opus 4.7
moonshot/kimi-k2.6 · anthropic/claude-opus-4.7
Kimi-K2.6 vs GPT-5.4
moonshot/kimi-k2.6 · openai/gpt-5.4
Gemini 3.1 Pro vs Kimi-K2.6
google/gemini-3.1-pro · moonshot/kimi-k2.6
Kimi-K2.6 vs Llama-4-Scout-17b-16e-Instruct
moonshot/kimi-k2.6 · meta/llama-4-scout-17b-16e-instruct
Claude Fable 5 vs DeepSeek V4 Pro
anthropic/claude-fable-5 · deepseek/deepseek-v4-pro
Claude Fable 5 vs Claude Opus 4.8
anthropic/claude-fable-5 · anthropic/claude-opus-4.8
Claude Fable 5 vs MiniMax M3
anthropic/claude-fable-5 · minimax/m3
Claude Fable 5 vs Gemini 3.1 Pro
anthropic/claude-fable-5 · google/gemini-3.1-pro
Claude Fable 5 vs GPT-5.5
anthropic/claude-fable-5 · openai/gpt-5.5
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
client.chat.completions.create(
    model="anthropic/claude-fable-5",
    messages=[{"role":"user","content":"hello"}],
)

# Kimi-K2.6
client.chat.completions.create(
    model="moonshot/kimi-k2.6",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →