Skip to content

> Google Jules

jules.google

Google Jules is an asynchronous coding agent that clones a connected GitHub repository into a Google Cloud VM, presents a plan for approval, then returns a diff and pull request. The no-cost tier is stated as 15 tasks per day and 3 concurrent tasks, while Jules in Google AI Pro provides 100 tasks per day and 15 concurrent tasks and Jules in Google AI Ultra provides 300 tasks per day and 60 concurrent tasks. Jules is described as language agnostic but works best with JavaScript/TypeScript, Python, Go, Java and Rust projects.

unknownbest-effort probe · checked never
Paid API Cloud agent, API keyFreemiumLow risk· conf 90%verified
// access — getting accessCloud agent

Jules API key for creating and managing cloud coding tasks.

Free credits
Not quantified
The no-cost tier is stated on jules.google as 15 tasks per day and 3 concurrent tasks, described in Google's blog as 'Introductory access to Jules'; no USD credit is published and daily task caps do not convert to a dollar amount.
Cheapest input /1M
Free
USD per 1M input tokens, best tracked model
Cheapest output /1M
Free
USD per 1M output tokens, best tracked model
Models tracked
46
Canonical models with normalized pricing
// source_analysisUprouter editorial analysis

// pros

  • The free tier is quantified on the official site as 15 tasks per day with 3 concurrent tasks, and paid tiers are published as 100 tasks/day with 15 concurrent (AI Pro) and 300 tasks/day with 60 concurrent (AI Ultra).
  • Task limits and concurrency are tracked as separate rows in Google's plan comparison, so concurrent execution capacity is a purchasing dimension independent of daily volume.
  • Jules does not train on private repository content, stated explicitly in the official FAQ, and each task runs in a fresh VM with the repo cloned into that environment.
  • Repository scope is controlled through GitHub's own app settings for Google Labs Jules, and Jules reads an AGENTS.md file at the repo root for project-specific context.
  • Jules is reachable from the web app, a CLI and an API, and notifies on task completion or when input is needed so tasks can be left running unattended.

// cons

  • Long-running processes such as npm run dev or watch scripts are not supported in setup scripts, which limits multi-service and live-preview workflows.
  • Repository access requires connecting GitHub, so other version-control hosts need additional integration work.
  • Jules is described on its own site as experimental and able to execute on any inputs and repositories it receives, with the FAQ placing responsibility for secrets, dependencies and unsafe commands on the user.
  • Plan limits are daily task counts rather than credits or token budgets, so cost cannot be modelled per unit of work and a task consumes a slot regardless of how small it is.

Use Jules for well-scoped background work such as tests, dependency bumps, documentation and small feature tickets, and keep credentials out of any repository it can read. Only move to a paid Google AI plan once 15 tasks per day becomes the binding constraint; at that point the increase in concurrency from 3 to 15 matters more than the raw task count.

// free_quota

Free tier present — value not quantified

This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.

note: The no-cost tier is stated on jules.google as 15 tasks per day and 3 concurrent tasks, described in Google's blog as 'Introductory access to Jules'; no USD credit is published and daily task caps do not convert to a dollar amount.

// pricinglast verified Sep 16, 2026
PlanTypeMonthlyInput /1MOutput /1MNote
Pay-as-you-gopayg———Billed based on cloud resource usage and agent tasks.
Jules (free)free———15 tasks/day (rolling 24h), 3 concurrent tasks, Gemini 2.5 Pro.
Jules in Pro (via Google AI Pro)subscription———100 tasks/day, 15 concurrent, higher access to latest models (starting with Gemini 3 Pro). Bundled into the Google AI Pro plan; Pro plan price not verified in this batch, so priceUsd left null.
Jules in Ultra (via Google AI Ultra)subscription$100.00/mo——300 tasks/day, 60 concurrent, priority access to latest models (starting with Gemini 3 Pro). Bundled into Google AI Ultra, launched at $100/month (blog.google, May 2026; gemini.google/subscriptions lists from $99.99/month).
pricing_last_verified: Sep 16, 2026official pricing page

Pricing normalized from public sources — always verify with the provider.

// model prices

ModelInput /1MOutput /1MContext
Google: Gemma 4 26B A4B (free)FreeFree262k
Google: Gemma 4 31B (free)FreeFree262k
Google: Lyria 3 Pro PreviewFreeFree1.0M
Google: Lyria 3 Clip PreviewFreeFree1.0M
Gemini 2.5 Pro$0.0000$0.00001.0M
gemini-3.1-pro-preview$0.0000$0.00001.0M
Google: Gemini 2.5 Flash Lite (batch)$0.050$0.2001.0M
Google: Gemma 3 4B$0.050$0.100131k
Google: Gemma 3 12B$0.050$0.150131k
Google: Gemma 3 27B$0.080$0.450131k
Gemma 4 26B A4B $0.090$0.300262k
Gemma 4 31B$0.090$0.340262k
Gemini 2.5 Flash Lite$0.100$0.4001.0M
Google: Gemini 3.1 Flash Lite (batch)$0.125$0.7501.0M
Google: Gemini 3.5 Flash Lite (batch)$0.150$1.251.0M
Google: Gemini 2.5 Flash (batch)$0.150$1.251.0M
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)$0.250$1.5066k
Google: Gemini 3.1 Flash Lite$0.250$1.501.0M
Gemini 3.1 Flash Lite Preview$0.250$1.501.0M
Google: Gemini 3 Flash Preview (batch)$0.250$1.501.0M
Google: Gemini 3.5 Flash Lite$0.300$2.501.0M
Google: Nano Banana (Gemini 2.5 Flash Image)$0.300$2.5033k
Google: Gemini 2.5 Flash$0.300$2.501.0M
Google: Gemini 3.8 Flash (batch)$0.375$1.881.0M
Google: Gemini 3.7 Flash (batch)$0.375$1.881.0M
Google: Gemini 3.6 Flash (batch)$0.375$1.881.0M
Google: Gemma 4 31B (batch)$0.390$0.970262k
Google: Nano Banana 2 (Gemini 3.1 Flash Image)$0.500$3.00131k
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)$0.500$3.0066k
Google: Gemini 3 Flash Preview$0.500$3.001.0M
Google: Gemini 2.5 Pro (batch)$0.625$5.001.0M
Gemma 2 27B$0.650$0.6508k
Google: Gemini 3.7 Flash$0.750$3.751.0M
Google: Gemini 3.6 Flash$0.750$3.751.0M
Google: Gemini 3.5 Flash (batch)$0.750$4.501.0M
Google: Gemini 3.1 Pro Preview (batch)$1.00$6.001.0M
Google: Gemini 2.5 Pro$1.25$10.001.0M
Google: Gemini 2.5 Pro Preview 06-05$1.25$10.001.0M
Google: Gemini 2.5 Pro Preview 05-06$1.25$10.001.0M
Google: Gemini 3.5 Flash$1.50$9.001.0M
Google: Nano Banana Pro (Gemini 3 Pro Image)$2.00$12.00131k
Google: Gemini 3.1 Pro Preview Custom Tools$2.00$12.001.0M
Google: Gemini 3.1 Pro Preview$2.00$12.001.0M
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)$2.00$12.0066k
Gemini 3.8 Flash——1.0M
Gemini 3 Pro (via Jules in Pro/Ultra)———
// faq
$ Does Google Jules have a free tier?

Yes — Google Jules offers a free tier. Always confirm current limits on Google Jules's official pricing page — free tiers change without notice.

$ How much does Google Jules cost per 1M tokens?

The cheapest model we track at Google Jules is Free per 1M input tokens and Free per 1M output tokens. This is normalized from Google Jules's published pricing — verify with the provider before purchasing, since prices change frequently.

$ Is Google Jules safe to use?

Uprouter rates Google Jules as low risk. Low risk: first-party from Google, with the free allowance stated on the plan cards — 15 tasks per day and 3 concurrent on Free (Pro 100/day, Ultra 300/day). The metering is task-based rather than token-based, so a "task" can consume very different amounts of compute; the limits are stable but coarse, and the product is a coding agent, not a general inference API. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.

// community0 reviews

Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.

No published reviews yet — be the first.

// more_informationprice history · live status · risk & confidence · code snippets

price_history

No recorded changes yet.

live_status

current: unknown

No probes recorded yet.

Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.

risk_&_confidence

Low risk
90%

Low risk: first-party from Google, with the free allowance stated on the plan cards — 15 tasks per day and 3 concurrent on Free (Pro 100/day, Ultra 300/day). The metering is task-based rather than token-based, so a "task" can consume very different amounts of compute; the limits are stable but coarse, and the product is a coding agent, not a general inference API.

Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.

code_snippets

# Google Jules's own API — get a key from their dashboard
curl https://jules.google/chat/completions \
  -H "Authorization: Bearer THEIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2-5-pro",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.

// similar_providersscored by Paid API signals

Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.