provider specs

what you need to know before integrating

providerpricing modelest. cost/querylatencyapi patterncitationsspecial capabilities
OpenAI o3
o3-deep-research
deprecated · shutdown 2026-12-11 → gpt-5.5-pro
per-token$1-10/query10-30+ minResponses API, async backgroundyes (inline annotations)
MCP serverscode interpreterfile searchweb search
OpenAI o4-mini
o4-mini-deep-research
deprecated · shutdown 2026-12-11 → gpt-5.5-pro
per-token$0.40-2.50/query3-10 minResponses API, async backgroundyes (inline annotations)
MCP serverscode interpreterfile searchweb search
Perplexity Sonar
sonar-deep-research
per-token + per-search$0.30-1.30/query1-3 minChat Completions (OpenAI-compatible), synchronousyes (inline + source URLs)
citation-focusedsearch groundingbilled per token + citation + reasoning + search
Gemini Deep Research
deep-research-preview-04-2026
per-token + per-search$1-3/task~20 min (60 min max)Interactions API, async (background=true)yes (url + file citations)
google searchurl contextcode executionMCPfile searchvisualizationmultimodal
Gemini Deep Research Max
deep-research-max-preview-04-2026
per-token + per-search$3-7/taskup to 60 minInteractions API, async (background=true)yes (url + file citations)
~160 searches/taskgoogle searchurl contextcode executionMCPfile searchvisualization
Parallel Pro
pro
per-request$0.10/query2-10 minTask API, async pollingyes (with excerpts)
structured JSON outputauto-schema1 of 9 tiers (lite→ultra8x)
Parallel Pro-Fast
pro-fast
per-request$0.10/query30s-5 minTask API, async pollingyes (with excerpts)
structured JSON outputauto-schemafaster variant (lower freshness)
Parallel Ultra
ultra
per-request$0.30/query5-25 minTask API, async pollingyes (with excerpts)
structured JSON outputauto-schemadeep research modeultra2x/4x/8x available
Parallel Ultra-Fast
ultra-fast
per-request$0.30/query1-10 minTask API, async pollingyes (with excerpts)
structured JSON outputauto-schemafaster variant (lower freshness)
Valyu DeepResearch
deepresearch (fast/standard/heavy/max)
per-request$0.10-15/task1 min - 3 hrREST, async (poll / webhook)yes (title + url)
SEC/academic/clinical/patent sourcesstructured JSON outputpython sandboxbrowser automation
You.com Research
research (lite→frontier)
per-request$0.012-0.45/query< 10s - 5 minREST, synchronousyes (with excerpts)
structured JSON outputsource control (domains/freshness)finance research variant
Exa Research
exa-research
per-request~$0.02-0.15/query (usage-based)~1-2 minResearch API, async pollingyes (excerpts + field grounding)
neural/semantic searchstructured output w/ groundingreturns real per-query cost

benchmarks

the RACE column is an independent academic benchmark (DeepResearch Bench, 2025 model versions). vendor scores are self-reported — note that DRACO is authored by Perplexity and Valyu's figures are its own re-run, so treat them as marketing, not neutral evals. every number links to its source. for a blind, community-run signal, see our arena leaderboard.