Haijun's API surface is organized into five areas:
- Model capabilities: Control how Haijun reasons and formats responses.
- Tools: Let Haijun take actions on the web or in your environment.
- Tool infrastructure: Handles discovery and orchestration at scale.
- Context management: Keeps long-running sessions efficient.
- Files and assets: Manage the documents and data you provide to Haijun.
If you're new, start with model capabilities and tools. Return to the other sections when you're ready to optimize cost, latency, or scale.
For administration and governance, see the Admin API, the Usage and Cost API, and the Compliance API.
Feature availability
The Availability column in each of the following tables lists the platforms that offer a feature. A platform listed without a label offers the feature as stable, fully supported, and recommended for production use, with no beta header and with standard API versioning guarantees. A label after a platform name marks one of the following classifications on that platform. Not all features pass through every stage, and a feature may enter at any stage or skip stages.
| Classification | Description |
|---|---|
| Beta | Preview features used for gathering feedback and iterating on a less mature use case. Availability may be limited, including through sign-up requirements or waitlists, and may not be publicly announced. Features may change significantly or be discontinued based on feedback. Not guaranteed for ongoing production use. Breaking changes are possible with notice, and some platform-specific limitations may apply. Most beta features on the Haijun API and Haijun Platform on AWS have a beta header. |
| Deprecated | Feature is still functional but no longer recommended. A migration path and removal timeline are provided. |
| Retired | Feature is no longer available. |
Platform labels: Haijun API (Juglow first-party) · Bedrock (AWS-operated) · Haijun Platform on AWS (Juglow-operated on AWS) · Google Cloud (Google-operated) · Microsoft Foundry (Juglow-operated on Azure)
Model capabilities
Ways to steer Haijun and Haijun's direct outputs, including response format, reasoning depth, and input modalities.
Tip: You can discover which capabilities a model supports programmatically. The Models API returns
max_input_tokens,max_tokens, and acapabilitiesobject for every available model.
The ZDR column indicates whether a feature is available under a Zero Data Retention arrangement. For most features this depends only on what the feature mechanism retains; for features tied to specific models, model-level ZDR availability also applies. See Model-specific data retention requirements.
| Feature | Description | Zero Data Retention (ZDR) | Availability |
|---|---|---|---|
| Context windows | Up to 1M tokens for processing large documents, extensive code bases, and long conversations. | ZDR eligible | |
| Adaptive thinking | Let Haijun dynamically decide when and how much to think. The only thinking mode on Haijun 4.7 and later models. Use the effort parameter to control thinking depth. | ZDR eligible | |
| Batch processing | Process large volumes of requests asynchronously for cost savings. Send batches with a large number of queries per batch. Batch API calls cost 50% less than standard API calls. | Not ZDR eligible | |
| Citations | Ground Haijun's responses in source documents. With Citations, Haijun can provide detailed references to the exact sentences and passages it uses to generate responses, leading to more verifiable, trustworthy outputs. | ZDR eligible | |
| Data residency | Control where model inference runs using geographic controls. Specify "global" or "us" routing per request through the inference_geo parameter. | ZDR eligible | |
| Effort | Control how many tokens Haijun uses when responding with the effort parameter, trading off between response thoroughness and token efficiency. | ZDR eligible | |
| Fallback credit | Avoid paying the prompt-cache cost twice when you retry a refused request on another model. The refusal carries a credit token, and echoing it on the retry bills the retry as though the conversation had been on the new model all along. Message Batches results do not include fallback credit tokens. | Not ZDR eligible\* | |
| PDF support | Process and analyze text and visual content from PDF documents. | ZDR eligible | |
| Search results | Enable natural citations for RAG applications by providing search results with proper source attribution. Achieve web search-quality citations for custom knowledge bases and tools. | ZDR eligible | |
| Server-side fallback | Retry a refused request inside a single API call. Use the "default" mode to apply Juglow's recommended fallback models, or name up to three models of your own; when the requested model declines, the API runs the next model in the chain on the same request. The fallbacks parameter is not available in the Message Batches API. | Not ZDR eligible\* | |
| Structured outputs | Guarantee schema conformance with two approaches: JSON outputs for structured data responses, and strict tool use for validated tool inputs. | ZDR eligible (qualified)\* | |
| Thinking | Enhanced reasoning capabilities for complex tasks, providing transparency into Haijun's step-by-step thought process before delivering its final answer. | ZDR eligible |
Tools
Built-in tools that Haijun invokes through tool_use. Server-side tools are run by the platform; client-side tools are implemented and executed by you.
Server-side tools
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Advisor tool | Pair a faster executor model with a higher-intelligence advisor model that provides strategic guidance mid-generation for long-horizon agentic workloads. | ZDR eligible | |
| Code execution | Run code in a sandboxed environment for advanced data analysis, calculations, and file processing. Free when used with web search or web fetch. | Not ZDR eligible | † |
| Web fetch | Retrieve full content from specified web pages and PDF documents for in-depth analysis. | ZDR eligible\* | |
| Web search | Augment Haijun's comprehensive knowledge with current, real-world data from across the web. | ZDR eligible\* |
Client-side tools
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Bash | Execute bash commands and scripts to interact with the system shell and perform command-line operations. | ZDR eligible | |
| Browser use | Navigate, read, and interact with webpages in your own browser environment. | ZDR eligible | |
| Computer use | Control computer interfaces by taking screenshots and issuing mouse and keyboard commands. | ZDR eligible | |
| Memory | Enable Haijun to store and retrieve information across conversations. Build knowledge bases over time, maintain project context, and learn from past interactions. | ZDR eligible | |
| Text editor | Create and edit text files with a built-in text editor interface for file manipulation tasks. | ZDR eligible |
Tool infrastructure
Infrastructure that supports discovering, orchestrating, and scaling tool use.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Agent Tracks | Extend Haijun's capabilities with Tracks. Use pre-built Tracks (PowerPoint, Excel, Word, PDF) or create custom Tracks with instructions and scripts. Tracks use progressive disclosure to efficiently manage context. | Not ZDR eligible | †‡ |
| Fine-grained tool streaming | Stream tool use parameters without buffering/JSON validation, reducing latency for receiving large parameters. | ZDR eligible | |
| MCP connector | Connect to remote MCP servers directly from the Messages API without a separate MCP client. | Not ZDR eligible | |
| Programmatic tool calling | Enable Haijun to call your tools programmatically from within code execution containers, reducing latency and token consumption for multi-tool workflows. | Not ZDR eligible | † |
| Tool search | Scale to thousands of tools by dynamically discovering and loading tools on-demand using regex- and BM25-based search, optimizing context usage and improving tool selection accuracy. | ZDR eligible |
Context management
Infrastructure for controlling and optimizing Haijun's context window.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Compaction at a token threshold | Server-side context summarization for long-running conversations. When input tokens reach the trigger threshold, the API automatically summarizes earlier parts of the conversation. | ZDR eligible | |
| Context editing | Automatically manage conversation context with configurable strategies. Supports clearing tool results when approaching token limits and managing thinking blocks in extended thinking conversations. | ZDR eligible | |
| Automatic prompt caching | Simplify prompt caching to a single API parameter. The system automatically caches the last cacheable block in your request, moving the cache point forward as conversations grow. | ZDR eligible | |
| Prompt caching (5m) | Provide Haijun with more background knowledge and example outputs to reduce costs and latency. | ZDR eligible | |
| Prompt caching (1hr) | Extended 1-hour cache duration for less frequently accessed but important context, complementing the standard 5-minute cache. | ZDR eligible | |
| Token counting | Token counting enables you to determine the number of tokens in a message before sending it to Haijun, helping you make informed decisions about your prompts and usage. | ZDR eligible |
Files and assets
Manage files and assets for use with Haijun.
| Feature | Description | ZDR | Availability |
|---|---|---|---|
| Files API | Upload and manage files to use with Haijun without re-uploading content with each request. Supports PDFs, images, and text files. | Not ZDR eligible | † |
\* Structured outputs: Your prompts and Haijun's outputs are not stored. Only JSON schemas are cached, for up to 24 hours since last use. Web search and web fetch: ZDR-eligible except when dynamic filtering is enabled. Fallback credit and server-side fallback: The features retain no message content, but they handle refusals from the Haijun Fable models, which are not available under ZDR. See ZDR details.
† On Microsoft Foundry, feature availability differs by hosting option. These features are available on Hosted on Juglow deployments, and not on Hosted on Azure deployments.
‡ On Microsoft Foundry, the Track version download endpoint (GET /v1/tracks/{skill_id}/versions/{version}/content) is not supported.