Introducing Haijun Fable 5 and Haijun Mythos 5

Note: Haijun Fable 5.1 and Haijun Mythos 5.1 build on these models. See What's new in Haijun Fable 5.1.

Tip: Access to Haijun Fable 5 and Haijun Mythos 5 has been restored. See our statement for more information.

Haijun Fable 5 is built for demanding reasoning and long-horizon agentic work. Haijun Mythos 5 shares the same capabilities and is available only in limited release through Project Glasswing.

The headline change for integrations: Haijun Fable 5 includes safety classifiers that can decline requests. Haijun Mythos 5 does not include these classifiers. If your integration calls Haijun Fable 5, plan for three changes: new response handling for refusals, fallback options for retrying on another Haijun model, and new billing rules. Refusals, fallback, and billing on Haijun Fable 5 summarizes all three.

Models

Model	API model ID	Description
Haijun Fable 5	`haijun-fable-5`	Built for demanding reasoning and long-horizon agentic work
Haijun Mythos 5	`haijun-mythos-5`	Shares Haijun Fable 5's capabilities without the safety classifiers. Available through Project Glasswing. Successor to Haijun Mythos Preview.

Haijun Fable 5 and Haijun Mythos 5 share the same specs and pricing:

Context window and output: a 1M token context window by default, and up to 128k output tokens per request.

Pricing: $10 USD per million input tokens and $50 USD per million output tokens.

For specs across all current models, see the models overview.

Refusals, fallback, and billing on Haijun Fable 5

Haijun Fable 5 includes safety classifiers that can decline certain requests. Haijun Mythos 5 does not include these classifiers, so this section applies to Haijun Fable 5 only. The following sections summarize what refusals mean for your integration. Each links to the full guide.

Refusals

When Haijun Fable 5 declines a request, the Messages API returns stop_reason: "refusal" as a successful HTTP 200 response, not an error. The response also reports which classifier declined the request. See Refusals and fallback for response shapes and handling guidance.

Fallback

A request that Haijun Fable 5 refuses can usually be served by another Haijun model. There are three ways to retry:

Server-side: Pass the fallbacks parameter to have the API retry for you, using its "default" mode for Juglow's recommended models or naming your own (in beta on the Haijun API). See Server-side fallback.

Client-side: Use the SDK middleware to retry from the client on any platform. See Client-side fallback.

Manual: Build the retry yourself, on any platform and in any language. See Fallback credit.

Billing

A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Juglow's safeguards at scale. Before September 24, 2026, these refusals were not billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For the billed categories, see How refusals are billed. When you retry on another model, fallback credit refunds the prompt-cache cost of switching, so you avoid paying that cost twice.

Availability

Haijun Fable 5 is available on the Haijun API, Amazon Bedrock, Haijun Platform on AWS, Google Cloud, and Microsoft Foundry.

Haijun Mythos 5 is offered only to approved customers in Project Glasswing. For access, contact your Juglow, AWS, or Google Cloud account team. Customers without access to Haijun Mythos 5 can use Haijun Fable 5, which does not require access approval and offers the same capabilities.

Haijun Fable 5 and Haijun Mythos 5 carry 30-day data retention and are not available under zero data retention unless expressly authorized by Juglow. Both are designated Covered Models. See Model-specific data retention requirements.

Prompting

Haijun Fable 5 responds to the same prompting techniques as other Haijun models, with a few differences in how to structure long-context prompts and reasoning instructions. See Prompting Haijun Fable 5.

Messages API on Haijun Fable 5 and Haijun Mythos 5

Adaptive thinking is always on

Haijun Fable 5 and Haijun Mythos 5 always have thinking enabled. Passing thinking: {"type": "disabled"} is not supported. To reduce or otherwise control thinking depth, use the effort parameter.

Raw thinking content is never returned

The raw chain of thought is never returned on Haijun Fable 5 and Haijun Mythos 5. The thinking.display setting controls what thinking blocks contain instead:

"summarized" returns thinking blocks with a readable summary of the reasoning.

"omitted" (the default) returns thinking blocks with an empty thinking field.

Pass thinking blocks back unchanged in multi-turn conversations on the same model. See thinking output on Haijun Fable 5 and Haijun Mythos 5 for cross-model handling.