# How Claude Video Estimates Token Cost for Different Detail Modes > Understand Claude Video token cost with four detail modes. Explore trade-offs in speed, fidelity, and token consumption from transcript-only to uncapped scene detection. - Repository: [bradautomates/claude-video](https://github.com/bradautomates/claude-video) - Tags: deep-dive - Published: 2026-08-02 --- **Claude Video uses a four-level detail dial that trades off extraction speed, visual fidelity, and token consumption, with costs ranging from 0 image tokens (transcript-only) to 22,800+ tokens (uncapped scene detection).** The `claude-video` repository by bradautomates implements a `/watch` skill that processes YouTube videos through Claude's vision API. The **token cost estimation** depends entirely on how many frames are extracted and sent to the model, controlled by the `--detail` flag parsed in [`skills/watch/scripts/watch.py`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/scripts/watch.py). --- ## Detail Modes and Their Token Costs The four modes use different **extraction engines** with varying frame caps. Each extracted frame becomes an image that Claude reads at approximately **197 tokens per frame** (calculated via Anthropic's formula: `(width × height) ÷ 750` for 512×288 px frames). | Mode | Engine | Frame Cap | Extraction Time | Image Tokens | |------|--------|-----------|-----------------|--------------| | `transcript` | None (text-only) | 0 | ~4.5 s | **0** (~26.6K text tokens) | | `efficient` | `ffmpeg -skip_frame nokey` | 50 | ~0.5 s | **~9,800** | | `balanced` | Scene-change detection | 100 | ~20.9 s | **~19,700** | | `token-burner` | Scene-change (uncapped) | Unlimited | ~21.0 s | **~22,800+** | Source measurements are documented in [`README.md`](https://github.com/bradautomates/claude-video/blob/main/README.md) under the "Detail modes — measured" section and in [`skills/watch/SKILL.md`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/SKILL.md). --- ## How Frame Extraction Maps to Token Cost ### Transcript Mode: Zero Image Tokens The **cheapest option** skips visual analysis entirely. In [`watch.py`](https://github.com/bradautomates/claude-video/blob/main/watch.py), this mode bypasses ffmpeg frame extraction and returns only Whisper transcripts or YouTube captions. ```bash # No image tokens consumed /watch https://youtu.be/example --detail transcript ``` ### Efficient Mode: Fast Key-Frame Sampling Uses `ffmpeg -skip_frame nokey` to grab up to **50 intra-coded frames** rapidly. The hard cap keeps token costs predictable for long videos. ```bash # ~50 frames, ~9,800 image tokens /watch https://youtu.be/example --detail efficient ``` ### Balanced Mode: Scene-Aware Default The **recommended default** runs scene-change detection with a **100-frame ceiling**. If scene detection fails, it falls back to uniform sampling. This mode appears in [`SKILL.md`](https://github.com/bradautomates/claude-video/blob/main/SKILL.md) as the "detail dial" sweet spot. ```bash # ~100 frames, ~19,700 image tokens (default) /watch https://youtu.be/example --detail balanced ``` ### Token-Burner Mode: Uncapped Fidelity Removes the frame cap entirely, keeping every detected scene change. A 49-minute test video yielded **116 frames** (~22,800 tokens). Use sparingly for analysis requiring maximum visual context. ```bash # Uncapped frames, highest token cost /watch https://youtu.be/example --detail token-burner ``` --- ## Overriding Token Budgets Manually The `--max-frames` argument in [`watch.py`](https://github.com/bradautomates/claude-video/blob/main/watch.py) allows capping any mode regardless of its default: ```bash # Force 40-frame maximum on balanced mode watch https://youtu.be/example --detail balanced --max-frames 40 ``` This overrides the built-in caps (50/100/unlimited) and directly controls token expenditure. --- ## Implementation Details in watch.py The token cost estimation logic resides in [`skills/watch/scripts/watch.py`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/scripts/watch.py). The script: 1. Parses `--detail` and `--max-frames` arguments 2. Selects the ffmpeg pipeline (key-frame skip, scene detection, or none) 3. Extracts frames to temp storage with timestamps 4. Returns frame paths for Claude's `Read` tool The **197 tokens per frame** calculation assumes default 512px width maintained across all modes. Actual costs scale linearly with frame count, making the `--detail` flag the primary cost control mechanism. --- ## Summary - **Token cost is frame-count linear**: Each extracted frame ≈ 197 image tokens via `(width × height) / 750` - **Four detail modes** provide predictable cost tiers: 0, ~10K, ~20K, or uncapped tokens - **`balanced`** is the default with 100-frame cap; **`transcript`** eliminates image tokens entirely - **Manual override** via `--max-frames` in [`watch.py`](https://github.com/bradautomates/claude-video/blob/main/watch.py) caps any mode's token consumption - Source documentation in [`README.md`](https://github.com/bradautomates/claude-video/blob/main/README.md) and [`skills/watch/SKILL.md`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/SKILL.md) provides measured benchmarks --- ## Frequently Asked Questions ### How does Claude Video calculate tokens per image frame? Claude Video applies Anthropic's documented formula: `(width × height) ÷ 750`. With the default 512×288 pixel frames, this yields approximately **197 tokens per frame**. The calculation is implicit in the token estimates provided in [`README.md`](https://github.com/bradautomates/claude-video/blob/main/README.md) rather than computed at runtime. ### Can I use Claude Video without consuming any image tokens? Yes. The **`transcript`** detail mode skips frame extraction entirely, consuming only text tokens (~26,600 for typical transcripts). Pass `--detail transcript` to [`watch.py`](https://github.com/bradautomates/claude-video/blob/main/watch.py) or the `/watch` skill to enable this mode. ### What happens if a video has more scene changes than the frame cap? In **`balanced`** mode, scene-change detection runs but results are truncated to the 100-frame cap. In **`token-burner`** mode, no cap applies—all detected scenes are preserved. The `--max-frames` flag can impose stricter limits on either mode. ### Where is the detail mode logic implemented in the codebase? The implementation spans three files: [`skills/watch/scripts/watch.py`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/scripts/watch.py) handles argument parsing and ffmpeg orchestration; [`skills/watch/SKILL.md`](https://github.com/bradautomates/claude-video/blob/main/skills/watch/SKILL.md) defines the skill contract; and [`README.md`](https://github.com/bradautomates/claude-video/blob/main/README.md) documents measured token benchmarks and usage patterns.