Claude Fable 5.1
Claude Fable 5.1 sits above the Opus line in Anthropic's Claude family, built for the most demanding reasoning, research and long-horizon agent work. It carries a 1M-token context window and a 128K output ceiling, takes text and images, and supports function calling. It decides for itself how long to think before it answers, and its thinking bills as output; on hard tasks a single answer can run for minutes, so stream long requests. It costs two and a half times Opus 5.5 per token: start with Opus 5.5, and move a workload to Fable 5.1 when Opus is not enough.
Pricing
Input
$10.00 / 1M
Output
$50.00 / 1M
Pay only for what you use. No subscriptions, no monthly minimum.
Specs
- Context
- 1M
- Max output
- 128K
- Latency
- Slow
- Category
- Text
- Arabic
- Strong
Quick start
Use any OpenAI-compatible client. Just change base_url and your key.
from openai import OpenAI
client = OpenAI(
api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
base_url="https://api.thalam.ai/v1",
)
response = client.chat.completions.create(
model="anthropic/claude-fable-5.1",
messages=[
{"role": "user", "content": "Hello from Thalam!"}
],
)
print(response.choices[0].message.content)Similar models
Gemini 4 Argon
Google's first Gemini 4 model and its newest frontier model, built for long, multi-step work in coding, finance, legal and research. 1M-token context, reasoning, and text, image, video and audio input. From 1 December 2026: $4.00 in / $20.00 out per 1M tokens.
GPT-6 Astra
OpenAI's GPT-6 generation. Frontier reasoning with a 1M-token context, image input, and adjustable reasoning effort.