Skip to main content
Fetch Hive tracks task costs by service. Most services have a fixed task credit cost. Some depend on provider usage, search depth, account model type, or number of generated images.

​
How task costs work

Hosted AI model calls, hosted agent calls, hosted prompt runs, hosted native search, and hosted image generation use the hosted LLM pool for provider usage. Each call still records a task count. Personal model calls use your connected provider account. They charge the platform task credits shown in the table and don’t add a hosted provider charge.

​
Workflow and model services

ServiceTask creditsNotes
AI Model1Hosted calls also include provider usage in the hosted LLM pool. Personal model calls cost 1 platform task credit.
Agent1Hosted agent calls also include provider usage in the hosted LLM pool. Personal model calls cost 1 platform task credit.
Prompt1Prompt runs use the same pricing path as AI model calls.
Image Generation1 per imageHosted image generation charges one task per generated image and includes provider usage in the hosted LLM pool. Personal image generation costs one platform task credit per image.
Google Search2 or 3Hosted searches up to depth 40 cost 2 credits. Depth above 40 or backup search costs 3 credits. Personal searches cost 0 credits.
Google Grounding1Hosted Gemini grounded results charge one task and provider usage in the hosted LLM pool. Personal Gemini grounding records the tool run without hosted LLM wallet credits.
Bing Search2 or 3Uses the same task cost rules as Google Search.
Google News2 or 3Uses the same task cost rules as Google Search.
Google AI Mode2Personal provider usage costs 0 credits.
Google AI Overview2Personal provider usage costs 0 credits.
Website Scrape1Fixed platform task credit cost.
Exa SearchVariableHosted calls are calculated from the Exa provider charge plus platform markup. Personal calls cost 1 credit.
Exa SimilarVariableHosted calls are calculated from the Exa provider charge plus platform markup. Personal calls cost 1 credit.
Copilot Search5Fixed platform task credit cost.
Custom API1Fixed platform task credit cost.
Slack1Fixed platform task credit cost.
Notion1Fixed platform task credit cost.
Google Docs1Fixed platform task credit cost.
Google Sheets1Fixed platform task credit cost.
PDF Generation1Fixed platform task credit cost.
Gmail1Fixed platform task credit cost.
URL to Screenshot1Fixed platform task credit cost.
Airtable1Fixed platform task credit cost.
Linear1Fixed platform task credit cost.
Write to Knowledge Base1Fixed platform task credit cost.
Search Knowledge Base1Fixed platform task credit cost.
Embedding1Embeddings use text-embedding-3-small by default.
Document URL0Fixed platform task credit cost.
Document Upload0Fixed platform task credit cost.
JSON Schema0Fixed platform task credit cost.
Custom Knowledge Base Item0Fixed platform task credit cost.

​
Agent tool calls

Agent tool calls are billed when the agent run records each completed tool call. Sub-agents bill through their child agent run instead of the parent tool call. Nested sub-agent costs, tokens, and task credits roll up through the parent chain, including failed child runs when they produced billable completion records. Execution timeout and depth/parallelism caps are controlled separately from trace and cost rendering.
Agent toolTask creditsNotes
GPT Search1Native OpenAI web search is recorded as a gpt_search tool call.
Vector Search1Vector search tool calls count as one task.
DataForSEO1Hosted DataForSEO calls also record the provider-side unit charge.
xAI Web Search1Hosted calls use the hosted LLM pool for provider usage.
X Search1Hosted calls use the hosted LLM pool for provider usage.
Anthropic Web Search1Completed hosted calls use the hosted LLM pool for provider usage.
Sub-agentBilled on child runThe child agent creates its own completions and task usage.

​
Structural services

ServiceTask creditsNotes
WorkflowBilled by child servicesA workflow step records the nested run result. The nested workflow’s own steps carry the task usage.
Iteration0Iteration records the fan-out or aggregate result. Steps inside the iteration carry their own task usage.
Condition0Conditions route execution and don’t create a billed service call.