Claude Fable 5.2
Anthropic's 9 Nov 2026 flagship and, on Artificial Analysis Intelligence Index v5.0.1, the top model on the board at 65 at max effort (62 at xhigh and high, 56 medium, 54 low) — five points clear of Gemini 4 Carbon at 60 on the same index. Priced at $8/$40 per 1M tokens, 20% below Fable 5.1, with cache reads at $0.20 (0.025x input); Anthropic says output is up to 30% faster and that Fable 5.2 blocks about 55% fewer requests unnecessarily than 5.1. Fast mode (research preview) is $16/$80. 1M context, 128K maximum output, adaptive thinking always on at a default effort of high, text and image in, text out, knowledge cutoff Jun 2026. Anthropic's own table has it at 49.1% on FrontierCode 2.0 at xhigh effort (Opus 5.5 45.5%, GPT-6 Astra 42.8%) and 89.3% on OSWorld 2.1, but not first everywhere: Gemini 4 Carbon leads AutomationBench and Opus 5.5 leads the AA-Briefcase Elo. The catch is cost per task: Artificial Analysis measures $26.54 per Index task at max, with 275M output tokens (median 72.8M) and 247.85s to the first answer token. Anthropic itself recommends starting with Opus 5.5 for most coding and knowledge work and reserving Fable for the most demanding long-horizon agentic work. High-risk cyber and biology requests are routed to Opus 4.8 / Opus 5 as a safety fallback.
1M
tokens
128K
tokens
$8
per 1M tokens
$40
per 1M tokens
101
tokens/sec
Nov 2026
2026-11-09
$24.00
per 1M tokens
4.2
quality per $
Capabilities
Benchmarks
Price vs Quality
Context Window in Context
- ▸ Claude Fable 5.21M
- GPT-4.11M
- Gemini 2.5 Pro1M
- Gemini 2.0 Flash1M
- Llama 4 Maverick1M
- GPT-5.51M
- GPT-5.5 Pro1M
- Claude Opus 4.71M
尚未接入我们的网关
Swfte Connect 尚未持有 Claude Fable 5.2 的密钥，因此这里没有可运行的内容。添加你自己的提供商密钥，就能用与本目录中其他模型相同的 API 调用它。
curl https://api.swfte.com/agents/v2/gateway/chat/completions \
-H "Authorization: Bearer $SWFTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic:claude-fable-5-2",
"messages": [{"role": "user", "content": "Hello"}]
}'About Claude Fable 5.2
Claude Fable 5.2 is a flagship AI model by Anthropic, released on November 9, 2026. It supports a context window of 1000K tokens and can generate up to 128K output tokens.
At $8 per million input tokens and $40 per million output tokens, its blended cost of $24.00/1M tokens places it in the premium pricing tier. Its value score of 4.2 reflects the balance of quality and cost.
Using Claude Fable 5.2 with Swfte
Access Claude Fable 5.2 through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try Claude Fable 5.2 in our AI Playground before integrating.