> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request.
> Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance.
> For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code.
> The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust.
> Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool.
> Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name <name> --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md.

# Context and Token Budgeting

> How to allocate prompt and output tokens for quality, speed, and cost.

Token budgeting is a core production skill. It directly affects latency, spend, and reliability.

## Token budget components

Total request footprint usually includes:

* System/developer instructions
* User prompt/input
* Retrieved context (RAG, docs, tools)
* Tool schemas/function definitions
* Model output tokens

## Why budgets matter

* Larger prompts increase latency and cost.
* Overlong prompts can degrade relevance if context quality is low.
* Tiny output budgets can cause truncation and invalid structured outputs.

Reasoning can consume the output budget before a model produces an answer. These
responses return HTTP 200 with the reasoning that was produced, without a fabricated
answer. Chat completions retain `reasoning_content` and `finish_reason: "length"`
when the output limit is reached. Responses retain the reasoning output item and
report `status: "incomplete"`. A normal provider stop remains `stop` or `completed`.

## Budgeting strategy

1. Set max input target per route.
2. Reserve output headroom for worst-case responses.
3. Trim low-value context aggressively.
4. Monitor real token usage distributions over time.

## Practical guardrails

* Enforce hard caps for input and output tokens.
* Add preflight truncation/summarization rules for large context.
* Use route-specific limits (search answer vs long-form generation).
* Validate outputs for truncation markers or partial JSON.

## Common mistakes

* Copying one token limit across all endpoints.
* Keeping verbose system prompts for every request class.
* Ignoring tool schema token overhead.

## Recommendation

Treat token budgets as configuration with continuous monitoring, not one-time setup.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.