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

# Token Use and Costs

# Token use & costs

WednesdayAI tracks **tokens**, not characters. Tokens are model-specific, but most
OpenAI-style models average \~4 characters per token for English text.

## How the system prompt is built

WednesdayAI assembles its own system prompt on every run. It includes:

* Tool list + short descriptions
* Skills list (only metadata; instructions are loaded on demand with `read`)
* Self-update instructions
* Workspace + bootstrap files (`AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, `BOOTSTRAP.md` when new, plus `MEMORY.md` and/or `memory.md` when present). Large files are truncated by `agents.defaults.bootstrapMaxChars` (default: 20000), and total bootstrap injection is capped by `agents.defaults.bootstrapTotalMaxChars` (default: 150000). `memory/*.md` files are on-demand via memory tools and are not auto-injected. Once the agent deletes `BOOTSTRAP.md` to complete onboarding, that file is no longer injected at all.
* Time (UTC + user timezone)
* Reply tags + heartbeat behavior
* Runtime metadata (host/OS/model/thinking)

See the full breakdown in [System Prompt](https://docs.wednesdayai.dev/next/developers/concepts/system-prompt).

## What counts in the context window

Everything the model receives counts toward the context limit:

* System prompt (all sections listed above)
* Conversation history (user + assistant messages)
* Tool calls and tool results
* Attachments/transcripts (images, audio, files)
* Compaction summaries and pruning artifacts
* Provider wrappers or safety headers (not visible, but still counted)

For images, WednesdayAI downscales transcript/tool image payloads before provider calls.
Use `agents.defaults.imageMaxDimensionPx` (default: `1200`) to tune this:

* Lower values usually reduce vision-token usage and payload size.
* Higher values preserve more visual detail for OCR/UI-heavy screenshots.

For a practical breakdown (per injected file, tools, skills, and system prompt size), use `/context list` or `/context detail`. See [Context](https://docs.wednesdayai.dev/next/developers/concepts/context.md).

## How to see current token usage

Use these in chat:

* `/status` → **emoji‑rich status card** with the session model, context usage,
  last response input/output tokens, and **estimated cost** (API key only).
* `/usage off|tokens|full` → appends a **per-response usage footer** to every reply.
  * Persists per session (stored as `responseUsage`).
  * OAuth auth **hides cost** (tokens only).
* `/usage cost` → shows a local cost summary from the configured session store
  (JSONL transcripts or the sqlite/postgres store).

Other surfaces:

* **TUI/Web TUI:** `/status` + `/usage` are supported.
* **CLI:** `wednesdayai status --usage` and `wednesdayai channels list` show
  provider quota windows (not per-response costs).

## Cost estimation (when shown)

Costs are estimated from your model pricing config:

```
models.providers.<provider>.models[].cost
```

These are **USD per 1M tokens** for `input`, `output`, `cacheRead`, and
`cacheWrite`. If pricing is missing, WednesdayAI shows tokens only. OAuth tokens
never show dollar cost.

## Cache TTL and pruning impact

Provider prompt caching only applies within the cache TTL window. WednesdayAI can
optionally run **cache-ttl pruning**: once the cache TTL has expired, it prunes
the session, and that trimmed view is sticky for the rest of the session. Later
requests keep the trimmed tool results so they do not re-cache the full history,
which keeps cache write costs lower when a session goes idle past the TTL.

Configure it in [Gateway configuration](https://docs.wednesdayai.dev/next/admin/gateway/configuration.md) and see the
behavior details in [Session pruning](https://docs.wednesdayai.dev/next/developers/concepts/session-pruning.md).

Heartbeat can keep the cache **warm** across idle gaps. If your model cache TTL
is `1h`, setting the heartbeat interval just under that (e.g., `55m`) can avoid
re-caching the full prompt, reducing cache write costs.

In multi-agent setups, you can keep one shared model config and tune cache behavior
per agent with `agents.list[].params.cacheRetention`.

For a full knob-by-knob guide, see [Prompt Caching](https://docs.wednesdayai.dev/next/developers/reference/prompt-caching.md).

For Anthropic API pricing, cache reads are significantly cheaper than input
tokens, while cache writes are billed at a higher multiplier. See Anthropic’s
prompt caching pricing for the latest rates and TTL multipliers:
[https://docs.anthropic.com/docs/build-with-claude/prompt-caching](https://docs.anthropic.com/docs/build-with-claude/prompt-caching)

### Example: keep 1h cache warm with heartbeat

```yaml theme={"dark"}
agents:
  defaults:
    model:
      primary: "anthropic/claude-opus-4-6"
    models:
      "anthropic/claude-opus-4-6":
        params:
          cacheRetention: "long"
    heartbeat:
      every: "55m"
```

### Example: mixed traffic with per-agent cache strategy

```yaml theme={"dark"}
agents:
  defaults:
    model:
      primary: "anthropic/claude-opus-4-6"
    models:
      "anthropic/claude-opus-4-6":
        params:
          cacheRetention: "long" # default baseline for most agents
  list:
    - id: "research"
      default: true
      heartbeat:
        every: "55m" # keep long cache warm for deep sessions
    - id: "alerts"
      params:
        cacheRetention: "none" # avoid cache writes for bursty notifications
```

`agents.list[].params` merges on top of the selected model's `params`, so you can
override only `cacheRetention` and inherit other model defaults unchanged.

### Example: enable Anthropic 1M context beta header

Anthropic's 1M context window is currently beta-gated. WednesdayAI can inject the
required `anthropic-beta` value when you enable `context1m` on supported Opus
or Sonnet models.

```yaml theme={"dark"}
agents:
  defaults:
    models:
      "anthropic/claude-opus-4-6":
        params:
          context1m: true
```

This maps to Anthropic's `context-1m-2025-08-07` beta header.

This only applies when `context1m: true` is set on that model entry.

Requirement: the credential must be eligible for long-context usage (API key
billing, or subscription with Extra Usage enabled). If not, Anthropic responds
with `HTTP 429: rate_limit_error: Extra usage is required for long context requests`.

If you authenticate Anthropic with OAuth/subscription tokens (`sk-ant-oat-*`),
WednesdayAI skips the `context-1m-*` beta header because Anthropic currently
rejects that combination with HTTP 401.

## Tips for reducing token pressure

* Use `/compact` to summarize long sessions.
* Trim large tool outputs in your workflows.
* Lower `agents.defaults.imageMaxDimensionPx` for screenshot-heavy sessions.
* Keep skill descriptions short (skill list is injected into the prompt).
* Prefer smaller models for verbose, exploratory work.

See [Skills](https://docs.wednesdayai.dev/next/users/tools/skills.md) for the exact skill list overhead formula.


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