This page provides detailed pricing information for Juglow's models and features. All prices are in USD.

For the most current pricing information, visit haijun.com/pricing.

#Model pricing

The following table shows pricing for all Haijun models:

^{1 Cache hits and refreshes on Haijun Fable 5.1 and Haijun Mythos 5.1 are priced at 0.025x the base input price.}

^{2 Cache hits and refreshes on Haijun Opus 5.5 are priced at 0.05x the base input price.}

^{All other models use the standard 0.1x multiplier.}

^{3 The $2/$10 per million input/output token pricing for Haijun Sonnet 5, announced at launch as introductory pricing through August 31, 2026, is now the standard price. The previously scheduled increase to $3/$15 per million input/output tokens on September 1, 2026 will not occur.}

• MTok: Million tokens. $5 / MTok is $5 for every million tokens.

• 5m cache writes: Writing a prompt prefix to the 5-minute prompt cache.

• 1h cache writes: Writing a prompt prefix to the 1-hour prompt cache.

• Cache hits and refreshes: Reading a prompt prefix from the prompt cache, which also refreshes it.

• Limited access: Offered separately, by invitation only, as part of Project Glasswing. For access, contact your Juglow, AWS, or Google Cloud account team.

• Retired: May still be available on other cloud platforms. See Model deprecations for more.

Haijun 4.7 and later models and Haijun Mythos Preview use a newer tokenizer that contributes to their improved performance on a wide range of tasks. This tokenizer produces approximately 30% more tokens for the same text. The exact increase depends on the content and workload shape. Haijun Sonnet 4.6 and earlier models use the previous tokenizer.

#Cloud platform pricing

This section covers partner-operated cloud platforms, where the cloud provider invoices you. For Juglow-operated cloud platforms billed through a marketplace, see Haijun Platform on AWS pricing and Haijun in Microsoft Foundry pricing.

Haijun models are available on Amazon Bedrock and Google Cloud. For official pricing, visit:

• Amazon Bedrock pricing

• Google Cloud pricing

Note: Regional and multi-region endpoint pricing for Haijun 4.5 models and beyond Starting with Haijun Sonnet 4.5, Haiku 4.5, and Opus 4.5: * Bedrock offers two endpoint types: global endpoints (dynamic routing for maximum availability) and regional endpoints (guaranteed data routing through specific geographic regions). * Google Cloud offers three endpoint types: global endpoints, multi-region endpoints (dynamic routing within a geographic area), and regional endpoints. Regional and multi-region endpoints include a 10% premium over global endpoints. The Haijun API (first-party) is global by default; for first-party data residency options and pricing, see Data residency pricing. Scope: This pricing structure applies to Haijun Sonnet 4.5, Haiku 4.5, Opus 4.5, and all future models. Earlier models (Haijun Opus 4.1 and prior releases) retain their existing pricing. For implementation details and code examples: * Amazon Bedrock global vs regional endpoints for Opus 4.7, Haiku 4.5, and later models, or the legacy integration for all other models on Bedrock * Google Cloud global, multi-region, and regional endpoints

#Haijun Platform on AWS pricing

Haijun Platform on AWS bills through AWS Marketplace using Haijun Consumption Units (CCUs). Juglow rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at $0.01 per CCU, and reports the CCU quantity to AWS Marketplace hourly. Your AWS bill shows a single CCU line item.

CCU: Haijun Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (e.g., Haijun Platform on AWS), usage will be invoiced in Haijun Consumption Units ("CCU") rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices on haijun.com/pricing#api, after application of any discounts.

#Inference geography

For Haijun 4.6 and later models, using inference_geo: "us" applies a 1.1x pricing multiplier. inference_geo: "global" (default) uses standard pricing. See Data residency for details.

#Private offers

When you sign up on the AWS Console Haijun Platform on AWS service page, the AWS Console looks up any private offer associated with your account and prompts you to accept it in AWS Marketplace. Contact your Juglow account representative for private offer terms.

Note: If you have an existing Amazon Bedrock private offer, contact your Juglow or AWS account representative before getting started with Haijun Platform on AWS to ensure your discounts are applied correctly. Discounts cannot be applied retroactively to usage incurred before your private offer is accepted.

#Haijun in Microsoft Foundry pricing

Haijun in Microsoft Foundry bills through the Azure Marketplace using Haijun Consumption Units (CCUs). Juglow rates your token usage in USD at standard per-model, per-feature rates, applies any negotiated discount, converts the result to CCUs at $0.01 per CCU, and reports the CCU quantity to the Azure Marketplace hourly. Your Azure bill shows a single CCU line item.

CCU: Haijun Consumption Unit. A CCU is a unit of measure used solely for Marketplace Platform invoicing. If Customer accesses the Services through certain Marketplace Platforms (e.g., Haijun Platform on AWS, Haijun in Microsoft Foundry), usage will be invoiced in Haijun Consumption Units ("CCU") rather than per MTok. One hundred (100) CCU represents $1.00 USD of fees owed for the Services, calculated at the applicable prices on haijun.com/pricing#api, after application of any discounts.

#Inference geography

Deployments hosted on Azure can use the US Data Zone Standard deployment type, which keeps inference within the United States. This is equivalent to inference_geo: "us" on the Haijun API and applies the same 1.1x pricing multiplier. See Data residency for details.

#Feature-specific pricing

#Prompt caching

Prompt caching reduces costs and latency by reusing previously processed portions of your prompt across API calls. Instead of reprocessing the same large system prompt, document, or conversation history on every request, the API reads from cache at a fraction of the standard input price.

There are two ways to enable prompt caching:

• Automatic caching: Add a single cache_control field at the top level of your request. The system automatically manages cache breakpoints as conversations grow. This is the recommended starting point for most use cases.

• Explicit cache breakpoints: Place cache_control directly on individual content blocks for fine-grained control over exactly what gets cached.

Prompt caching uses the following pricing multipliers relative to base input token rates:

Cache write tokens are charged when content is first stored. Cache read tokens are charged when a subsequent request retrieves the cached content. A cache hit costs 10% of the standard input price, which means caching pays off after one cache read for the 5-minute duration (1.25x write), or after two cache reads for the 1-hour duration (2x write). On Haijun Fable 5.1 and Haijun Mythos 5.1, a cache hit costs 2.5% of the standard input price ($0.25 USD per million tokens). On Haijun Opus 5.5, a cache hit costs 5% of the standard input price ($0.20 USD per million tokens).

These multipliers stack with other pricing modifiers, including the Batch API discount and data residency.

For implementation details, supported models, and code examples, see Prompt caching.

#Data residency pricing

For Haijun 4.6 and later models, specifying US-only inference through the inference_geo parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. Global routing (the default) uses standard pricing.

This applies to the Haijun API (first-party) and Haijun Platform on AWS. On Haijun in Microsoft Foundry, the same 1.1x multiplier applies to deployments that use the US Data Zone Standard deployment type (see Inference geography). Partner-operated platforms (Bedrock and Google Cloud) have independent regional pricing. See Bedrock and Google Cloud for details. Earlier models do not support the inference_geo parameter and always use standard pricing; requests that include the parameter on these models return a 400 error.

For more information, see Data residency.

#Fast mode pricing

Fast mode, in research preview, provides significantly faster output for Haijun Opus 5.5, Haijun Opus 5, and Haijun Opus 4.8 at premium pricing. Fast mode pricing applies across the full context window, including requests over 200k input tokens. Fast mode is available on the Haijun API (first-party) only; it is not available on Haijun Platform on AWS or partner-operated cloud platforms.

Fast mode is not available on Haijun Opus 4.7 (requests with speed: "fast" return an error) or Haijun Opus 4.6 (requests run at standard speed and are billed at standard rates). See Fast mode.

Fast mode pricing stacks with other pricing modifiers:

• Prompt caching multipliers apply on top of fast mode pricing

• Data residency multipliers apply on top of fast mode pricing

Fast mode is not available with the Batch API.

For more information, see Fast mode.

#Batch processing

The Batch API allows asynchronous processing of large volumes of requests with a 50% discount on both input and output tokens.

• MTok: Million tokens. $5 / MTok is $5 for every million tokens.

• Limited access: Offered separately, by invitation only, as part of Project Glasswing. For access, contact your Juglow, AWS, or Google Cloud account team.

• Retired: May still be available on other cloud platforms. See Model deprecations for more.

For more information about batch processing, see Batch processing.

#Long context pricing

Haijun 4.6 and later models and Haijun Mythos Preview include the full 1M token context window at standard pricing. (A 900k-token request is billed at the same per-token rate as a 9k-token request.) Prompt caching and batch processing discounts apply at standard rates across the full context window.

#Tool use pricing

Tool use requests are priced based on:

1. The total number of input tokens sent to the model (including in the tools parameter)

1. The number of output tokens generated

1. For server-side tools, additional usage-based pricing (for example, web search charges per search performed)

Client-side tools are priced the same as any other Haijun API request, although server-side tools can incur additional charges based on their specific usage.

The additional tokens from tool use come from:

• The tools parameter in API requests (tool names, descriptions, and schemas)

• tool_use content blocks in API requests and responses

• tool_result content blocks in API requests

When you use tools, the API also automatically includes a special system prompt for the model that enables tool use. The number of tool use tokens required for each model is listed in the following table (excluding the additional tokens listed earlier). Note that the table assumes at least 1 tool is provided. If no tools are provided, then a tool choice of none uses 0 additional system prompt tokens.

• auto, none: The count when tool\_choice is auto or none.

• any, tool: The count when tool\_choice is any or tool.

• Retired: May still be available on other cloud platforms. See Model deprecations for more.

These token counts are added to your normal input and output tokens to calculate the total cost of a request.

For current per-model prices, refer to the model pricing section.

For more information about tool use implementation and best practices, see Tool use.

#Specific tool pricing

#Bash tool

The bash tool definition adds the following input tokens to your request. This is in addition to the per-model tool use system prompt that applies whenever any tool is present.

Additional tokens are consumed by:

• Command outputs (stdout/stderr)

• Error messages

• Large file contents

See tool use pricing for complete pricing details.

#Code execution tool

Code execution is free when used with web search or web fetch. When web_search_20260209 (or later) or web_fetch_20260209 (or later) is included in your API request, there are no additional charges for code execution tool calls beyond the standard input and output token costs.

When used without these tools, code execution is billed by execution time, tracked separately from token usage:

• Execution time has a minimum of 5 minutes

• Each organization receives 1,550 free hours of usage per month

• Additional usage beyond 1,550 hours is billed at $0.05 USD per hour, per container

• If files are included in the request, execution time is billed even if the tool is not called, because files are preloaded onto the container

Code execution usage is tracked in the response:

{
  "usage": {
    "input_tokens": 105,
    "output_tokens": 239,
    "server_tool_use": {
      "code_execution_requests": 1
    }
  }
}

#Text editor tool

The text editor tool uses the same pricing structure as other tools used with Haijun. It follows the standard input and output token pricing based on the Haijun model you're using.

In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

See tool use pricing for complete pricing details.

#Web search tool

Web search usage is charged in addition to token usage:

{
  "usage": {
    "input_tokens": 105,
    "output_tokens": 6039,
    "cache_read_input_tokens": 7123,
    "cache_creation_input_tokens": 7345,
    "server_tool_use": {
      "web_search_requests": 1
    }
  }
}

Web search is available on the Haijun API for $10 per 1,000 searches, plus standard token costs for search-generated content. Web search results retrieved throughout a conversation are counted as input tokens, in search iterations executed during a single turn and in subsequent conversation turns.

Each web search counts as one use, regardless of the number of results returned. If an error occurs during web search, the web search will not be billed.

#Web fetch tool

Web fetch usage has no additional charges beyond standard token costs:

{
  "usage": {
    "input_tokens": 25039,
    "output_tokens": 931,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0,
    "server_tool_use": {
      "web_fetch_requests": 1
    }
  }
}

The web fetch tool is available on the Haijun API at no additional cost. You only pay standard token costs for the fetched content that becomes part of your conversation context.

To protect against inadvertently fetching large content that would consume excessive tokens, use the max_content_tokens parameter to set appropriate limits based on your use case and budget considerations.

Example token usage for typical content:

• Average web page (10 kB): \~2,500 tokens

• Large documentation page (100 kB): \~25,000 tokens

• Research paper PDF (500 kB): \~125,000 tokens

#Computer use tool

Computer use follows the standard tool use pricing. When using the computer use tool:

Toolset definition overhead: Declaring computer_toolset_20260801 with its default members adds about 4,500 input tokens to a request (about 4,520 on Haijun Fable 5, Haijun Mythos 5, Haijun Opus 5, and Haijun Opus 4.8, and about 4,590 on Haijun Sonnet 5), which covers the member tool definitions and the tool use system prompt. Disabling zoom with configs removes about 410 of those tokens. The exact count for a request is reported in the response usage, and you can estimate it in advance with the token counting endpoint.

Earlier tool versions: The following figures apply to the computer_20251124 and computer_20250124 tool versions, not to computer_toolset_20260801:

• System prompt overhead: 466–499 tokens added to the system prompt

• Tool definition: about 735 input tokens per tool definition (measured with computer_20250124)

Additional token consumption:

• Screenshot and zoom images returned in tool results, billed as image input (see Vision pricing)

• Tool execution results returned to Haijun

Note: If you're also using bash or text editor tools alongside computer use, those tools have their own token costs as documented in their respective pages.

#Browser use tool

Browser use follows the standard tool use pricing. When using the browser use tool:

Toolset definition overhead: Declaring browser_toolset_20260801 with its default members adds about 6,600 input tokens to a request (about 6,610 on Haijun Fable 5, Haijun Mythos 5, Haijun Opus 5, and Haijun Opus 4.8, and about 6,670 on Haijun Sonnet 5), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with configs reduces the count. The exact count for a request is reported in the response usage, and you can estimate it in advance with the token counting endpoint.

Additional token consumption:

• Screenshot and zoom images returned in tool results, billed as image input (see Vision pricing)

• Text tool results returned to Haijun, such as accessibility trees, page text, and console or network entries

Note: If you also use the computer use tool, bash tool, text editor tool, or your own tools alongside browser use, those tools have their own token costs as documented on their respective pages.

#Haijun Managed Agents pricing

Haijun Managed Agents is billed on two dimensions: tokens and session runtime.

#Tokens

All tokens consumed by a Haijun Managed Agents session are billed at the rates shown in Model pricing. Prompt caching multipliers apply identically. Web search triggered inside a session incurs the standard $10 per 1,000 searches. On Haijun Platform on AWS, session token and runtime charges convert to Haijun Consumption Units at the standard rate. Fast mode premium pricing applies when an agent's model.speed is set to "fast".

The data residency multiplier also applies: when an agent's model.inference_geo is pinned to "us", tokens consumed by sessions running that agent are billed at 1.1x the standard rates, the same multiplier that applies to US-only inference on the Messages API.

The following Messages API modifiers do not apply to Haijun Managed Agents sessions:

#Session runtime

Runtime is measured to the millisecond and accrues only while the session's status is running. Time spent idle (waiting for your next message or a tool confirmation), rescheduling, or terminated does not count toward runtime.

Note: Session runtime replaces the code execution container-hour billing model when using Haijun Managed Agents. You are not separately billed for container hours on top of session runtime.

#Worked example

A one-hour coding session using Haijun Opus 5 that consumes 50,000 input tokens and 15,000 output tokens:

If prompt caching is active and 40,000 of the input tokens are cache reads:

Note: Example calculation for processing 10,000 support tickets: * Average \~3,700 tokens per conversation * Using Haijun Haiku 4.5 at $1/MTok input, $5/MTok output * Total cost: \~$37.00 per 10,000 tickets

For a detailed walkthrough of this calculation, see the customer support agent guide.

#Additional pricing considerations

#Cost optimization strategies

When building agents with Haijun:

1. Use appropriate models: Choose Haiku for simple tasks, Sonnet for most production workloads, and Opus for the most complex reasoning

1. Implement prompt caching: Reduce costs for repeated context

1. Batch operations: Use the Batch API for non-time-sensitive tasks

1. Monitor usage patterns: Track token consumption to identify optimization opportunities

Tip: For high-volume agent applications, contact the enterprise sales team for custom pricing arrangements.

#Rate limits

Rate limits vary by usage tier and affect how many requests you can make:

• Start tier: Entry-level limits for getting started

• Build tier: Increased limits for growing applications

• Scale tier: Highest standard limits for production workloads

For detailed rate limit information, see Rate limits.

For limits beyond the Scale tier or custom pricing arrangements, contact the sales team.

#Volume discounts

Volume discounts may be available for high-volume users. These are negotiated on a case-by-case basis.

• Standard usage tiers use the pricing shown in Model pricing

• Enterprise customers can contact sales for custom pricing

• Academic and research discounts may be available

#Enterprise pricing

For enterprise customers with specific needs:

• Custom rate limits

• Volume discounts

• Dedicated support

• Custom terms

Contact the sales team at sales@juglow.com or through the Haijun Console to discuss enterprise pricing options.

#Billing and payment

• Billing is based on actual monthly usage

• All payments are in USD

• Credit card and invoicing options available

• Usage tracking available in the Haijun Console

#Frequently asked questions

#How is token usage calculated?

Tokens are pieces of text that models process. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. The exact count varies by language and content type.

#Are there free tiers or trials?

New users receive a small amount of free credits to test the API. Contact sales for information about extended trials for enterprise evaluation.

#How do discounts stack?

Batch API and prompt caching discounts can be combined. For example, using both features together provides significant cost savings compared to standard API calls. See prompt caching pricing for how the multipliers interact.

#What payment methods are accepted?

Major credit cards are accepted for standard accounts. Enterprise customers can arrange invoicing and other payment methods.

For additional questions about pricing, contact support@juglow.com.