Skip to main content

Models, Limits, Tokens, and Response Quality

Identify model-selection, approval, usage and runtime problems before retrying.

Check progress before retrying

An approval or connection request gives you a next step to complete. Read the action card or reconnect prompt before sending the task again. Before repeating a send, update or code execution, check the completed results and the connected app. A tool-run limit is separate from your credit allowance; match the remedy to the exact message.

Models, Limits, Tokens, and Response Quality

Use this guide when a model is missing, Auto selected a different model than expected, a response feels slow or low quality, a request hit a limit, or usage looks higher than expected.

Why a model may be missing or unavailable

  • Your admin, MSP, tenant, or role may restrict which models or Auto are available.

  • Some models are available only in certain product surfaces, features, or API compatibility paths.

  • Some models support tools, images, files, or long context better than others.

  • A model can be temporarily unavailable because of provider availability, product rollout, or usage limits.

  • The live model selector or API model list is the source of truth for what your account can use right now.

How Auto model selection works

Auto chooses the intelligence for the task within the options available to your account. Start with Auto for everyday work, or choose an available named model when you have a preference. Auto Model Selection explains its benefits and controls.

How credits, tokens, and context relate

  • Tokens: the text and structured content the model processes as input and output.

  • Context: the conversation history, files, instructions, tool results, and other information included with a request.

  • Model multiplier: a directional comparison of how credit-intensive a model is relative to a reference model. Use it to compare relative model usage; the task’s input, output and tools determine its total usage.

  • Credits: Hatz Credits measure usage across AI activity. Usage can vary by model, multiplier, input size, output size, files, tools, API calls, generated files, and workflow complexity.

  • Workflows and agents: multi-step runs, tool calls, files, retries, and generated outputs can consume credits across multiple pieces of work.

If usage is higher than expected, check the model choice, prompt length, files, tools, workflow step count, retries, generated files, and whether a long chat is carrying more context than intended. For more detail, see Credits & Usage, Getting More From Every Credit, Extra Usage, and Rate Limiting and Credit Overage.

Limits and common error classes

  • Credit or quota limit: the tenant, role, user, model, workflow, API key, or package may have reached a usage limit.

  • Rate or concurrency limit: too many requests may be running at once, or a provider may be throttling requests.

  • Context limit: the prompt, files, conversation history, tool schemas, or prior outputs may be too large for the selected route. For long-running chats, starting a fresh chat and restating the key context can help.

  • Timeout or retry failure: the request may have taken too long, failed upstream, or failed during a tool, file, or workflow step.

  • Unsupported feature: the selected model or API compatibility route may not support the requested tool, file, image, streaming, provider-specific option, or response shape.

Why responses can feel slow or lower quality

  • Large prompts, long chats, large files, tool calls, web search, document generation, and multi-step workflows can take longer.

  • Auto mode can choose a different model for different messages, so behavior may vary inside one conversation.

  • AI output quality depends on task clarity, model fit, instructions, files, context, and tool results.

  • To improve an answer, state the result you want, provide the relevant files or context, and ask for a specific correction. Choose Auto or an available named model for the task.

When support can help

Contact Support for a missing model, unexpected limit, repeatable error or a result that has changed unexpectedly.

Include the chat or run link, the error message, what you expected and what you tried.

Model and provider behavior changes over time, so use the current in-product model selector or API model list for live availability.

Did this answer your question?