At a glance — Oct 2026
Updated 2026-10-27 · forward this page: /jtbds/self-host-browser#briefScores as of 2026-09-14 (43 days old; Depot marks scores stale after 30 days). The pick is still Depot's current editorial pick; it has not been re-reviewed since. Prices below carry their own dates.
- Depot Pick
- Steel.dev · 8.27/10 for this job (curated estimate, high confidence)
lockInRisk low + capability.
- Runner-up
- Browserless · 8.25/10
Scores higher than the pick on: Capability fit, Latency / reliability, Maturity / track record.
- When not to use the pick
- No ops — Browserbase.
- Lock-in / migration
- The pick has lower stored lock-in risk than runner-up Browserless (2.5 vs 3.5). Pick exit signals: open source (provider tag `oss`); self-hostable (provider tag `self-host`). Self-host fallback listed for this job: Playwright, BrowserGym, Crawl4AI.
- Sourced price (usd_per_browser_hour)
Pick's lowest sourced SKU: Scale browser hours $0.08 (usd_per_browser_hour) — source, as of 2026-10-03
Cheapest matching SKU: Steel.dev Scale browser hours $0.08 — source, as of 2026-10-03. The pick is the cheapest.
Price history: first seen 2026-10-03 · last changed no change recorded · history JSON
- Free option
- Failure modes to watch
- Non-determinism: Run the task more than once and compare the end state, not a single transcript. Record the trial count next to any success rate you cite.
- Benchmark protocol mismatch: Store assisted-or-not, subset, and harness version beside every cited score. Refuse a ranking that mixes those fields.
- Collateral side effects: Snapshot the workspace or app state, then diff it against an allowlist. A passing check plus an unexpected diff is a failure.
- Confirmation skip: Gate those tool names on an approval id recorded before the call. A missing approval is a failure even if the downstream tool returns success.
- Context overflow: If the input exceeds the window, say so and retrieve a narrower slice. Do not answer from a truncated head as if it were the whole source.
- GUI grounding miss: After each GUI action, compare the resulting screen or accessibility tree to the control the plan named. Stop when they differ.
Cite: Agent Provider Depot, Depot Pick for self-host-browser: steel-dev, scores as of 2026-09-14. Agents: GET /api/decide?jtbd=self-host-browser
Free Self-host browser automation options · All sourced prices, cheapest first · for browser agents · for local-offline agents
Steel.dev
lockInRisk low + capability.
Pricing (directional): As of 2026-09-14 (docs.steel.dev/overview/pricinglimits): Launch **$0 + usage** ($30 one-time free credits/90d); Scale **$250 + usage** ($100 credits/mo); Enterprise custom. Browser hours Launch **$0.10/hr** / Scale **$0.08/hr** (per-minute…
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Pick Steel when you need to self-host browsers or hate SaaS lock-in. Browserbase wins on polish.
Quote for Self-host browser automation
Depot Pick stays Steel.dev. Prices below are sourced SKU rows only (as of 2026-10-27). Input and output are not blended. GET /api/quote?jtbd=self-host-browser
Only 1 candidate has a matching USD per browser-hour; nothing was compared, so pickIsPriceWinner is null.
- Browser tools usd_per_1k_calls $5 source as of 2026-10-03
- Scale dedicated IP usd_per_ip_month $5 source as of 2026-10-03
- Launch browser hours usd_per_browser_hour $0.1 source as of 2026-10-03
- Launch CAPTCHA solves usd_per_1k_solves $3 source as of 2026-10-03
- Launch proxy bandwidth usd_per_gb $10 source as of 2026-10-03
- Scale browser hours usd_per_browser_hour $0.08 source as of 2026-10-03
- Scale CAPTCHA solves usd_per_1k_solves $1 source as of 2026-10-03
- Scale plan usd_per_month $250 source as of 2026-10-03
- Scale proxy bandwidth usd_per_gb $6 source as of 2026-10-03
2 of 3 candidates have no sourced price row. 2 are excluded from the USD per browser-hour comparison (browser_hour). min sourced browser-hour among candidates; lowest browser-hour tier per provider; not quality-adjusted; proxy per GB, CAPTCHA solves, monthly plans, and chat tokens were not included
Runners-up
When NOT to use the top pick
No ops — Browserbase.
Full ranking (score table)
Ranked with this JTBD's weights. Scores are curated estimates unless marked otherwise. Agents: prefer /api/decide then this table for tie-breaks.
| # | Provider | Overall | Fit | $/perf | Latency | DX | As of |
|---|---|---|---|---|---|---|---|
| 1 | Steel.devDepot Pick | 8.3 | 8.6 | 8.5 | 8.0 | 8.6 | 2026-09-14 |
| 2 | Browserless | 8.3 | 8.8 | 7.8 | 8.6 | 8.5 | 2026-09-14 |
| 3 | Cloudflare Browser Rendering | 8.0 | 7.8 | 8.8 | 8.6 | 8.2 | 2026-09-14 |
Score methodology for this job
lockInRisk low + capability.
capabilityFit: 25%pricePerformance: 18%latencyReliability: 15%developerDx: 15%privacyPosture: 10%lockInRisk: 7%maturity: 10%