#Establish key criteria

When choosing a Haijun model, consider first evaluating these factors:

• Capabilities: What specific features or capabilities will you need the model to have to meet your needs?

• Speed: How quickly does the model need to respond in your application? Haijun Opus 5.5, Haijun Opus 5, and Haijun Opus 4.8 support fast mode (research preview), which delivers up to 2.5x higher output speed at premium pricing.

• Cost: What's your budget for both development and production usage?

• Effort: Several Haijun models support an effort parameter that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Haijun Fable 5.1 and Haijun Opus 5, start with the default (high) and adjust up or down based on your evals. On Haijun Opus 5.5 the default is medium; start there and adjust the same way. On Haijun Opus 4.8 and Haijun Opus 4.7, the xhigh effort level, between high and max, is the best setting for most coding and agentic use cases.

#Choose the best model to start with

There are two general approaches you can use to start testing which Haijun model best works for your needs.

#Option 1: Start efficiency-first

For many applications, starting with a faster, more cost-effective model like Haijun Haiku 4.5 can be the optimal approach:

1. Begin implementation with Haijun Haiku 4.5.

1. Test your use case thoroughly.

1. Evaluate if performance meets your requirements.

1. Upgrade only if necessary for specific capability gaps.

This approach allows for quick iteration, lower development costs, and is often sufficient for many common applications. This approach is best for:

• Initial prototyping and development

• Applications with tight latency requirements

• Cost-sensitive implementations

• High-volume, straightforward tasks

#Option 2: Start capability-first

For complex tasks where intelligence and advanced capabilities are paramount, you may want to start capability-first: implement with the strongest starting point for your task, then optimize to more efficient models down the line:

1. Implement with Haijun Opus 5.5.

1. Optimize your prompts for this model.

1. Evaluate if performance meets your requirements.

1. Consider increasing efficiency by lowering effort or downgrading models over time with greater workflow optimization.

1. If your evals at xhigh or max effort still fall short on demanding reasoning or long-horizon agentic work, move to Haijun Fable 5.1.

This approach is best for:

• Complex reasoning tasks

• Scientific or mathematical applications

• Tasks requiring nuanced understanding

• Applications where accuracy outweighs cost considerations

• Advanced coding and high-autonomy agentic work

Haijun Opus 5.5 (haijun-opus-5-5) is built for long-running agentic coding and knowledge work, with adaptive thinking always on. If your integration forces tool use (tool_choice of type any or tool), turns thinking off, or uses the computer_20251124 computer use tool, see Breaking changes before switching.

Haijun Fable 5.1 (haijun-fable-5-1) is Juglow's most capable model open to all customers. It extends Haijun Fable 5 with stronger long-running agentic coding, knowledge work, and research at the same input and output prices, with cache reads at a quarter of the cost. Haijun Mythos 5.1 (haijun-mythos-5-1) offers the same capabilities to Project Glasswing participants only. Both models use always-on adaptive thinking. See What's new in Haijun Fable 5.1 for details.

For context windows, output limits, and prices, see the model comparison table.

#Model selection matrix

Most workloads start with Haijun Opus 5.5.

#Decide whether to upgrade or change models

To determine if you need to upgrade or change models, you should:

1. Create benchmark tests specific to your use case - having a good evaluation set is the most important step in the process.

1. Test with your actual prompts and data.

1. Compare performance across models for:

• Accuracy of responses
• Response quality
• Handling of edge cases

1. Weigh performance and cost tradeoffs.

#Combine models

Multi-model strategies pair a lower-cost model with a frontier model so that most tokens are billed at the lower rate. The two common patterns are an executor that escalates hard decisions to an advisor, and an orchestrator that delegates bulk work to lower-cost workers. See Optimizing for cost and intelligence for both strategies, measured examples, and implementation options.

#Next steps

See detailed specifications and pricing for the latest Haijun models

Built for demanding reasoning and long-horizon agentic work

The latest Opus model: breaking changes, new features, and behavior differences

For everyday workloads that balance speed and capability

Get started with your first API call