Open beta Zabio is in open beta: anyone can sign up and use it in production. Models, prices and features can still change while we learn from the first customers. Tell us what breaks at hello@zabio.ai.
All news
anthropicAnnouncement

Claude Fable 5.2 and Claude Mythos 5.2 read other models' thinking blocks

Claude Fable 5.2 and Claude Mythos 5.2 read thinking blocks from Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 on the API.

Models:Claude Mythos 5.2

On Zabio today

  • claude-fable-5-2Live. Call it by name, or let auto pick it when it fits the job.Price and details
  • claude-opus-5-5Live. Call it by name, or let auto pick it when it fits the job.Price and details
  • claude-sonnet-5-5Live. Call it by name with your Zabio key.Price and details
  • claude-haiku-5-5Live. Call it by name with your Zabio key.Price and details
  • claude-fable-5-1Live. Call it by name, or let auto pick it when it fits the job.Price and details
Start free, no card needed

What changed

Claude Fable 5.2 and Claude Mythos 5.2 now read thinking blocks from other models on the Claude API and on Claude Models on Google Cloud (Google managed). The other models are Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5. On those platforms, a conversation that moves onto either model keeps its reasoning. No other model reads thinking blocks from Claude Fable 5.2 or Claude Mythos 5.2. When a conversation moves from either one to a model outside this pair, the API drops those blocks, including a move to Claude Opus 5.5 or Claude Fable 5.1. The request still succeeds. Dreams (research preview) now supports Claude Fable 5.2.

Key details

  • Thinking blocks from Claude Sonnet 5.5, Claude Haiku 5.5, Claude Fable 5.2, and Claude Mythos 5.2 are tied to the account that produced them.
  • The API drops those blocks without an error when another account sends them, unless the two accounts are linked.

What it means for Zabio customers

Reasoning from Claude Fable 5.2 or Claude Mythos 5.2 stays with a conversation only while it remains on one of those two models.

Breaking changes and migration

If your code switches models in one conversation, keep sending the full history. The API drops thinking blocks that the current model cannot read, without an error.

Source

Claude Fable 5.2 and Claude Mythos 5.2 read other models’ thinking blocks on the Claude API and Claude Models on Google Cloud (Google managed). So on those platforms, a conversation that moves onto either model keeps its reasoning.

Original announcement: Claude Platform release notes

How it compares

The models in this story next to models of the same class at a similar price, all available with one Zabio key.

ModelInput, $/MOutput, $/MCached, $/MContext window1,000 callsWriting code, hard
claude-fable-5-2AnthropicIn this story8.0040.000.201,000,000$36.0082.9
claude-opus-5-5AnthropicIn this story4.0020.000.201,000,000$18.0084.2
claude-sonnet-5-5AnthropicIn this story2.0010.000.101,000,000$9.0080.6
claude-haiku-5-5AnthropicIn this story0.100.500.011,000,000$0.4563.4
claude-fable-5-1AnthropicIn this story10.0050.000.251,000,000$45.0083.8
gpt-6.2-astraOpenAI8.0040.000.408,192$36.00no data
kimi-k3.1-pro-highspeedMoonshot AI4.0020.000.201,048,576$18.00no data
gemini-4-neonGoogle3.0015.00no data200,000$13.50no data

Prices are the vendor list prices in USD per million tokens. "1,000 calls" is 1,000 requests of 2,000 input tokens and 500 output tokens each, without caching. Zabio bills the list price plus its service fee: see pricing.

Scores: percent correct for that kind of job, aggregated from public results by Epoch AI, LMArena, and LiveBench, read on 16 November 2026. Epoch AI: CC BY 4.0, LMArena: CC BY 4.0, LiveBench: Leaderboard results used with attribution; the 2.0 release states no terms of its own (read 2026-11-06); the first version's Mathematics, Language, IF results: Code Apache 2.0 and MIT; leaderboard results used with attribution

Source: Claude Platform release notes (2026-11-09)