Create each key on its own page, paste it below, then copy the finished lines into your project's .env file. What you paste stays in this tab. It is never sent to Wirestack or saved.
On November 9, 2026 Anthropic released Claude Fable 5.2 (claude-fable-5-2) and Claude Mythos 5.2 (claude-mythos-5-2). Fable 5.2 is open to all Claude API customers. Mythos 5.2 is only for organizations verified through Anthropic's verification programs, such as the Cyber Verification Program.
1M token context window and 128k max output tokens. Adaptive thinking is always on; control its depth with effort.
Price: $8 per million input tokens and $40 per million output tokens. Fable 5.1 and Mythos 5.1 cost $10 and $50. Batch is $4 and $20.
Fast mode for Fable 5.2 costs $16 and $80 per million tokens.
Both models need 30-day data retention and are not available under zero data retention unless Anthropic authorizes it.
Four changes from Fable 5.1 can break your code:
The prefix check applies to every account. If your code changes the system prompt, the tools or an earlier message and then sends back a 5.2 thinking block, the request returns a 400 error (The block is bound to a different conversation). On Fable 5.1 this only hit accounts created on or after August 31, 2026.
Only Fable 5.2 and Mythos 5.2 read Fable 5.2 thinking blocks. Moving a conversation from 5.2 to any other model drops that reasoning. The request still succeeds.
The old computer_20251124 tool returns 400 on every platform except Amazon Bedrock. Use the computer_toolset_20260801 toolset.
Advisor tool (beta): a 5.2 executor accepts only claude-fable-5-2 or claude-mythos-5-2 as its advisor.
Prerequisites
An Anthropic API key in ANTHROPIC_API_KEY
Steps
Change your model ID from claude-fable-5-1 to claude-fable-5-2.
If your code builds the messages array itself, keep system and tools the same for the whole conversation, only add to messages, and send each assistant turn back exactly as the API returned it.
As a stopgap while you fix an edit, send the thinking-binding-controls-2026-08-01 beta header and set thinking.block_binding.prefix_mismatch_behavior to "drop_block". Anthropic warns this can raise output tokens.
Move computer use from computer_20251124 to computer_toolset_20260801.
If you use the advisor tool with a 5.2 executor, set the advisor's model to claude-fable-5-2 in new conversations (changing it counts as an edit to tools).
thinking: {"type": "enabled"} with budget_tokens, thinking: {"type": "disabled"} and forced tool_choice (any or a named tool) return 400 on 5.2. Omit thinking or send {"type": "adaptive"}, and keep tool_choice on auto.
Test it
Run your evals on claude-fable-5-2, starting at the default effort high. Then send a multi-turn conversation with thinking through your own code and confirm no request returns The block is bound to a different conversation.
Not confirmed
Anthropic's model pages do not name the first SDK versions that list the new model IDs; a plain string model ID works with any SDK version.
Wirestack