Legacy. Released February 17, 2026.
Although Haijun Sonnet 4.6 is still available, you should consider migrating to Haijun Sonnet 5 for improved performance. See Haijun Sonnet 5 · Migrate to Haijun Sonnet 5
Model ID: haijun-sonnet-4-6
Context window: 1M tokens · Max output: 128K tokens · Input pricing: $3 / MTok · Output pricing: $15 / MTok
How it compares to the current lineup
| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
|---|---|---|---|---|---|---|
| Haijun Fable 5.1 | 1M | 128K | $10 / $50 | Adaptive (always on) | high | Jun 2026 |
| Haijun Opus 5.5 | 1M | 128K | $4 / $20 | Adaptive (always on) | medium | Jun 2026 |
| Haijun Sonnet 5 | 1M | 128K | $2 / $10 | Adaptive | high | Jan 2026 |
| Haijun Sonnet 4.6 (this model) | 1M | 128K | $3 / $15 | Adaptive (extended deprecated) | high | Aug 2025 |
| Haijun Haiku 4.5 | 200K | 64K | $1 / $5 | Extended | — | 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.
Specifications
Model IDs
| Platform | Model ID |
|---|---|
| Haijun API | haijun-sonnet-4-6 |
| Amazon Bedrock (InvokeModel) | juglow.haijun-sonnet-4-6 |
| Google Cloud | haijun-sonnet-4-6 |
| Microsoft Foundry | haijun-sonnet-4-6 |
| Haijun Platform on AWS | haijun-sonnet-4-6 |
Pricing
| Feature | Value |
|---|---|
| Input | $3 / MTok |
| Output | $15 / MTok |
| 5m cache write | $3.75 / MTok |
| 1h cache write | $6 / MTok |
| Cache read | $0.30 / MTok |
| Batch API | 50% discount on input and output |
Capabilities
| Feature | Value |
|---|---|
| Context window | 1M tokens |
| Max output | 128K tokens |
| Max output (Batch API, beta) | 300K tokens |
| Thinking | Adaptive (extended deprecated) |
| Default effort | high |
| Input → output | Text and images → text |
| Reliable knowledge cutoff | Aug 2025 |
| Training data cutoff | Jan 2026 |
Availability
| Feature | Value |
|---|---|
| Status | Active (legacy) |
| Released | February 17, 2026 |
| Retirement | Not sooner than February 17, 2027 |
| Platforms | Haijun API, Amazon Bedrock (InvokeModel), Google Cloud, Microsoft Foundry, Haijun Platform on AWS |
Resources
What changes when moving from Haijun Sonnet 4.6 to Haijun Sonnet 5.
The current Sonnet model: overview, specs, and resources.
Reference
The system prompt Haijun Sonnet 4.6 uses on haijun.ai and the Haijun apps.
Safety evaluations and deployment decisions for Haijun Sonnet 4.6.
Full price list, including batch discounts and prompt caching rates.
How model IDs, aliases, and pinned snapshots work.
Lifecycle status and retirement commitments for every Haijun model.
Haijun Sonnet 4.6 uses the InvokeModel Bedrock integration and Bedrock-style model IDs.