Built for AI coding agents

Research API for AI coding agents.

Give Codex, Claude Code, Cursor, or your own agent a fast research tool for dependency choices, migration risk, market scans, and PR-ready evidence. It returns citations, typed JSON, and hard budget limits instead of another open-ended browser loop.

~90s
Lite mode for quick agent checks
20
sources in Standard mode
202
async response for background work
AI coding agent
/v1/research
Agent question

“Can I safely migrate this Vite dashboard to React Router v7 in this PR?”

00s
Agent calls the research tool

A coding agent asks for fresh docs, changelogs, and repo context before editing.

09s
Parallel retrieval fanout

Fluxweave searches, fetches, chunks, and filters sources under a fixed budget.

72s
Typed answer returns

The agent receives a recommendation, citations, risk notes, and next steps for the PR.

20
credits
5
sources
JSON
ready
Request · POST /v1/research
curl https://api.infrence.ai/v1/research \
  -H 'Authorization: Bearer inf_live_…' \
  -H 'Content-Type: application/json' \
  -d '{
  "question": "Find the current React Router v7 breaking changes before editing this routing PR",
  "mode": "lite"
}'
Response · 200 OK · 72.1s
20 credits
{
  "id": "9b0a4f12-7e3a-4c2b-9e1d-3f4c5a6b7c8d",
  "status": "succeeded",
  "credits_charged": 20,
  "brief": "React Router v7 keeps most v6 route objects intact, but framework mode and data APIs changed around bundling, typegen, and server/runtime config. For this PR, keep the current BrowserRouter path unless you also plan the framework-mode migration.",
  "typed": {
    "recommendation": "stay_on_library_mode_for_this_pr",
    "risk": "medium",
    "agent_next_steps": [
      "scan for createBrowserRouter usage",
      "avoid framework-mode file routes in this diff",
      "open a follow-up migration issue"
    ]
  },
  "sources": [
    { "url": "https://reactrouter.com/upgrading/v6", "title": "Upgrade from v6", "domain": "reactrouter.com" },
    { "url": "https://reactrouter.com/start/framework/routing", "title": "Framework routing", "domain": "reactrouter.com" },
    { "url": "https://github.com/remix-run/react-router", "title": "React Router repository", "domain": "github.com" }
  ],
  "latency_ms": 72184
}
Research speed

Pick a latency envelope per agent task.

AI coding agents should not wait for deep research on every turn. Route quick checks to Lite, deeper migrations to Standard or Pro, and background investigations to Max.

Agent taskModeWall-clockCreditsOutput
Pre-edit dependency checkLite~90s205 sources, fast brief
PR planning or migration researchStandard~4 min6520 sources, synthesis pass
Risky architecture decisionPro~8 min24560 sources, citation check
Background deep diveMaxup to 15 mincapped120 sources, metered
Production-ready

Research your agent can safely use.

Fluxweave turns the parts coding agents struggle with into explicit primitives: source policy, cost ceilings, structured answers, and auditable citations.

Latency caps per agent task

Use Lite for loop-time dependency checks, Standard for PR planning, Pro when the agent needs citation validation.

Typed answers your agent can branch on

Pass a JSON Schema and get structured fields like recommendation, risk, sources, and next_steps.

Citations for every handoff

Each answer returns title, URL, domain, and source summaries so humans can audit the agent before merge.

Async jobs for long runs

Return 202 immediately, stream progress over SSE, or post a signed webhook when the research is ready.

Source policy controls

Allowlist docs, changelogs, GitHub, package registries, or block domains your agent should never cite.

Budgeted instead of unbounded

Every request accepts a credit ceiling. Failed validation refunds, and cancelled jobs release reserved credits.

Pricing

Cost controls for unattended agents.

$0.01 per credit on packs. No subscription required, no card on file, and every request can set the maximum spend before work begins.

Starter
$5
500 credits

Try it. No subscription, no card on file.

Buy Starter
Handful
$20
2,000 credits

Enough for a week of building.

Buy Handful
Workshop
$50
5,000 credits

For an active prototype or side project.

Buy Workshop
Warehouse
$200
20,000 credits

PAYG ceiling — past this, a plan saves money.

Buy Warehouse
Plans

Save when agents run research every day.

Heavy usage? Subscribe for lower per-credit cost and higher concurrency.

Free
Free
500 cr / mo
Plan details →
Developer
$29/mo
4,000 cr / mo
Saves above 2,900 cr/mo
Plan details →
Startup
Popular
$149/mo
25,000 cr / mo
Saves above 14,900 cr/mo
Plan details →
Growth
$499/mo
100,000 cr / mo
Saves above 49,900 cr/mo
Plan details →
Fixed modes

Same endpoint, different depth.

Agents can choose cheaper, faster research for small code edits and reserve deeper work for decisions that will survive code review.

ModeCreditsList priceIncludes
Lite20$0.205 sources, ~90s
Standard65$0.6520 sources, ~4 min
Pro245$2.4560 sources, ~8 min, citation check
Maxmeteredyour max_creditsUp to your max_credits, 120 sources, ~15 min
Live demo

Inspect real research before wiring it into your agent.

Browse published briefs or submit a topic. It is the fastest way to judge citation quality, answer shape, and the kinds of questions Fluxweave handles well.

migrationReact Router v7 upgrade risk for a Vite app
libraryZod vs Valibot for schema validation in edge workers
securityRecent npm supply-chain incidents affecting build tools

Put fresh research in your coding agent loop.

500 free credits, no card required. Start with a Lite request, then move deeper when the agent needs more evidence.

Start building