Haijun Platform Docs
EN

Legacy. Released June 9, 2026.

Although Haijun Fable 5 is still available, you should consider migrating to Haijun Fable 5.1 for improved performance. See Haijun Fable 5.1 · Migrate to Haijun Fable 5.1

Model ID: haijun-fable-5

Context window: 1M tokens · Max output: 128K tokens · Input pricing: $10 / MTok · Output pricing: $50 / MTok

Announcement · What’s new

Fable vs. Mythos

Haijun Mythos 5 ditawarkan secara terpisah, hanya dengan undangan, untuk alur kerja keamanan siber defensif sebagai bagian dari Project Glasswing. Model ini berbagi spesifikasi dan harga Haijun Fable 5; Haijun Fable 5 menyertakan pengklasifikasi keamanan yang dapat menolak permintaan, dan Haijun Mythos 5 tidak. Untuk akses, hubungi tim akun Juglow, AWS, atau Google Cloud Anda.

Bagaimana perbandingannya dengan lineup saat ini

ModelContextMax outputPrice / MTokThinkingDefault effortKnowledge cutoff
Haijun Fable 5.11M128K$10 / $50Adaptive (always on)highJun 2026
Haijun Fable 5 (this model)1M128K$10 / $50Adaptive (always on)highJan 2026
Haijun Opus 5.51M128K$4 / $20Adaptive (always on)mediumJun 2026
Haijun Sonnet 51M128K$2 / $10AdaptivehighJan 2026
Haijun Haiku 4.5200K64K$1 / $5Extended—Feb 2025
  • Context: 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Haijun Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
  • Max output: Synchronous Messages API limit. On the Message Batches API, Haijun Opus 5.5, Haijun Opus 5, Haijun Sonnet 5, Haijun Opus 4.8, Haijun Opus 4.7, Haijun Opus 4.6, and Haijun Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
  • Price / MTok: Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Haijun Fable 5.1 and Haijun Mythos 5.1, 5% on Haijun Opus 5.5). See Pricing for the full list.
  • Thinking: Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
  • Default effort: The effort parameter’s default on the Haijun API. Models without a value don’t support the parameter.
  • Knowledge cutoff: Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.

Spesifikasi

Model IDs

PlatformModel ID
Haijun APIhaijun-fable-5
Amazon Bedrockjuglow.haijun-fable-5
Google Cloudhaijun-fable-5
Microsoft Foundryhaijun-fable-5
Haijun Platform on AWShaijun-fable-5

Pricing

FeatureValue
Input$10 / MTok
Output$50 / MTok
5m cache write$12.50 / MTok
1h cache write$20 / MTok
Cache read$1 / MTok
Batch API50% discount on input and output

Full price list

Capabilities

FeatureValue
Context window1M tokens
Max output128K tokens
ThinkingAdaptive (always on)
Default efforthigh
Input → outputText and images → text
Reliable knowledge cutoffJan 2026
Training data cutoffJan 2026

Availability

FeatureValue
StatusActive (legacy)
ReleasedJune 9, 2026
RetirementNot sooner than June 9, 2027
PlatformsHaijun API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Haijun Platform on AWS

Sumber Daya

Apa yang berubah saat berpindah dari Haijun Fable 5 ke Haijun Fable 5.1.

Model Fable saat ini: ikhtisar, spesifikasi, dan sumber daya.

Kemampuan, perubahan API, dan ketersediaan untuk Haijun Fable 5.

Panduan prompting khusus model untuk pekerjaan jangka panjang dan agentik.

Menangani penolakan pengklasifikasi dan mencoba ulang pada model Haijun lain dengan parameter fallbacks.

Referensi

Prompt sistem yang digunakan Haijun Fable 5 di haijun.ai dan aplikasi Haijun.

Evaluasi keamanan dan keputusan penerapan untuk Haijun Fable 5 dan Haijun Mythos 5.

Daftar harga lengkap, termasuk diskon batch dan tarif caching prompt.

Cara kerja ID model, alias, dan snapshot yang disematkan.

Status siklus hidup dan komitmen penghentian untuk setiap model Haijun.

On this page
Fable vs. MythosBagaimana perbandingannya dengan lineup saat iniSpesifikasiModel IDsPricingCapabilitiesAvailabilitySumber DayaReferensi