TinyFish for AI agents: benchmark results
TinyFish had the lowest cost per finished task on scrape (0.43¢) and search (1.31¢), counting API and model spend, failures included. No API charge was recorded for its calls on the test account, so that figure is mostly the model's spend. Check TinyFish's current pricing for your own volume.
Against Firecrawl, on the same tasks: scrape 90% vs 90% of tasks done, at 0.43¢ vs 1.22¢ per finished task; search 73% vs 85% of tasks done, at 1.31¢ vs 3.04¢ per finished task. They finished the same number of scrape tasks. The search gap in tasks done is too small to rule out chance. Firecrawl vs TinyFish, track by track.
TinyFish (content API) was tested on scrape and search, not on map and crawl. It got the same tasks, the same model (Claude Haiku 5.5), the same prompt and the same limits as every other provider, and a script checked every answer. TinyFish here means its Fetch API for scrape and its Search API for search.
Scrape 60 tasks · Read one page and pull out exact fields: prices, versions, install commands.
- Tasks done
- 90%
- 54 of 60
- 95% interval
- 80%–92%
- Cost per finished task
- 0.43¢
- Median time
- 3.5 s
2nd of 8 on tasks done, tied with 2 others. TinyFish is behind Context.dev (92%), but the gap of 2 points is too small to rule out chance.
Raw output, no model: the API's own response held every answer on 50 of 55 applicable tasks (91%), with no API charge recorded.
| Provider | Tasks done | 95% interval | Cost per finished task | Median time |
|---|---|---|---|---|
| Context.dev | 55 of 60 (92%) | 90%–100% | 0.72¢ | 3.7 s |
| Linkup | 54 of 60 (90%) | 90%–90% | 0.60¢ | 3.4 s |
| Firecrawl | 54 of 60 (90%) | 90%–90% | 1.22¢ | 3.3 s |
| TinyFish | 54 of 60 (90%) | 80%–92% | 0.43¢ | 3.5 s |
| Scrapfly | 53 of 60 (88%) | 80%–90% | 0.61¢ | 5.0 s |
| Jina | 52 of 60 (87%) | 60%–92% | 0.57¢ | 3.8 s |
| Browserbase | 49 of 60 (82%) | 78%–100% | 1.12¢ | 3.3 s |
| Spider | 12 of 60 (20%) | 4%–100% | 2.48¢ | 4.6 s |
Search 60 tasks · Find a fact on the live web: a package's latest version, a filing figure, a release date.
- Tasks done
- 73%
- 44 of 60
- 95% interval
- 47%–96%
- Cost per finished task
- 1.31¢
- Median time
- 5.3 s
4th of 5 on tasks done. TinyFish is behind Firecrawl (85%), but the gap of 12 points is too small to rule out chance.
Raw output, no model: the API's own response held every answer on 25 of 53 applicable tasks (47%), with no API charge recorded.
| Provider | Tasks done | 95% interval | Cost per finished task | Median time |
|---|---|---|---|---|
| Firecrawl | 51 of 60 (85%) | 69%–100% | 3.04¢ | 11 s |
| Linkup | 50 of 60 (83%) | 65%–97% | 2.55¢ | 5.3 s |
| Context.dev | 45 of 60 (75%) | 52%–96% | 1.82¢ | 5.2 s |
| TinyFish | 44 of 60 (73%) | 47%–96% | 1.31¢ | 5.3 s |
| Browserbase | 23 of 60 (38%) | 21%–59% | 5.97¢ | 12 s |
Read these numbers with
- TinyFish wasn't given a tuned run: its plan offered no affordable alternate preset.
TinyFish compared
- Firecrawl vs TinyFish scrape and search, compared with Firecrawl
- Context.dev vs TinyFish scrape and search, compared with Context.dev
- Linkup vs TinyFish scrape and search, compared with Linkup
- TinyFish vs Browserbase scrape and search, compared with Browserbase