browser-use/browser-use
120 source files scanned · 50 LLM call site(s) · ~0% of LLM spend looks recoverable (static heuristics)
$12.8per 10k runs today (gpt-4.1-mini, ~2000 prompt tokens)
$12.8per 10k runs with fixes applied
[](https://tokenzero.sh/audit/browser-use/browser-use)
Models referenced
gpt-4.1-mini ×6claude-sonnet-4-0 ×2gemini-2.0-flash-exp ×1gemini-2.5-flash-image-preview ×1gpt-4o ×1 (cheaper sibling: gpt-4o-mini)deepseek-v3-0324 ×1gpt-4.1 ×1 (cheaper sibling: gpt-4.1-mini)grok-4 ×1gpt-5-mini ×1
Findings
| Severity | Where | Finding | Est. |
|---|---|---|---|
| low | examples/features/custom_system_prompt.py:24 | "gpt-4.1-mini" retires on 2027-01-14 The provider announced on 2026-10-14 that this model retires on 2027-01-14 (80 days). Recommended replacement: gpt-6-luna. Fix: Move to gpt-6-luna (eval first); TokenZero's cascade can route to it, and the gateway warns in X-TokenZero-Warning until you do. | 0% |
| low | examples/features/fallback_model.py:35 | "gpt-4o" retires on 2027-01-14 The provider announced on 2026-10-14 that this model retires on 2027-01-14 (80 days). Recommended replacement: gpt-6-luna. Fix: Move to gpt-6-luna (eval first); TokenZero's cascade can route to it, and the gateway warns in X-TokenZero-Warning until you do. | 0% |
| low | examples/features/small_model_for_extraction.py:16 | "gpt-4.1" retires on 2027-01-14 The provider announced on 2026-10-14 that this model retires on 2027-01-14 (80 days). Recommended replacement: gpt-6-luna. Fix: Move to gpt-6-luna (eval first); TokenZero's cascade can route to it, and the gateway warns in X-TokenZero-Warning until you do. | 0% |
| low | examples/models/gpt-5-mini.py:16 | "gpt-5-mini" retires on 2026-12-11 The provider announced on 2026-06-11 that this model retires on 2026-12-11 (46 days). Recommended replacement: gpt-5.6-terra. Fix: Move to gpt-5.6-terra (eval first); TokenZero's cascade can route to it, and the gateway warns in X-TokenZero-Warning until you do. | 0% |
| info | examples/apps/ad-use/ad_generator.py:133 | Unrecognised model id "gemini-2.0-flash-exp" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
| info | examples/models/claude-4-sonnet.py:19 | Unrecognised model id "claude-sonnet-4-0" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
| info | examples/models/novita.py:33 | Unrecognised model id "deepseek-v3-0324" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
| info | examples/models/openrouter.py:17 | Unrecognised model id "grok-4" Not in the current pricing table: it may be retired or renamed. Retired models return errors or are silently remapped by some providers. Fix: Check the provider model list; TokenZero flags unpriced models in `X-TokenZero-Warning`. | 0% |
Fix all of it with one line
OPENAI_BASE_URL=https://tokenzero.sh/v1 ANTHROPIC_BASE_URL=https://tokenzero.sh
Keys pass through untouched. Cache formatting and exact caching are on by default; cascade routing stays opt-in. How it works