Head to head · Image generation · October 2026 research run

Google Imagen vs Leonardo.Ai API

Google Imagen shut down on 2026-08-17. Leonardo.Ai API scores 37.9 (F) on agent readiness against Google Imagen's 6.8 (F), and leads in 5 of 7 scored categories. Google Imagen leads on transparency & trust. Both do image generation.

Best image generation for AI agents · All 136 image comparisons

Which one, for what

Google Imagen F

Best for Nothing new. It shut down on 2026-08-17.

Ahead on

  • Transparency & trust, 60 against 50

Watch for

Discontinued. Google lists the Imagen endpoints as shut down on both the Gemini API and Vertex AI

Leonardo.Ai API F

Best for Canva-adjacent creative teams who want Leonardo's own models and several third-party ones on one balance.

Ahead on

  • Reliability, 30 against 0
  • Schema & documentation, 70 against 25
  • Agent ergonomics, 54 against 0
  • Security & auth, 40 against 0
  • Maintenance & community, 38 against 5

Also in its favour

  • Still running. Google Imagen has shut down
  • Rated higher by the reviewer agents, 2.0 against 1.0 out of 5

Watch for

No per-image price list outside the logged-in calculator

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent ergonomics Leonardo.Ai API +54

Google Imagen 0

Nothing callable remains, so context cost, error handling and retries can't be assessed (0).

Leonardo.Ai API 54

Results come back as image URLs, and the hosted MCP server does image generation only (20). Pagination and output filters not checked in this run (5). Limit errors undocumented (8). No idempotency key. Webhook callbacks on the key avoid polling (6). Official TypeScript and Python SDKs (15).

Schema & documentation Leonardo.Ai API +45

Google Imagen 25

What's left is documentation, re-read on 11 November at aistudio.google.com, where the Gemini API docs now live. No OpenAPI or other contract for the retired endpoints (0). The llms.txt indexes the Imagen migration page and an Imagen 4 model page as Markdown, but there's no live surface for it to document, read as openai-sora reads its llms.txt (0). The Imagen migration page states the shutdown and the three changes needed and names gemini-2.5-flash-image or gemini-3.1-flash-image, while the deprecations table names gemini-nano-banana-2.1 for every Imagen model and the changelog deprecated gemini-3.1-flash-image on 6 October 2026 (5). The parameter reference is gone (0). Migration steps but no worked example on the page (5). Dated changelog and a deprecations table with release and shutdown dates for every Imagen version (15). 0+0+5+0+5+15 = 25.

Leonardo.Ai API 70

The Markdown API reference that llms.txt links for the v2 generations endpoint carries an OpenAPI 3.0.0 definition, with a model discriminator mapping 85 request shapes; it documents only the 200 response and v1 endpoints aren't covered (20). llms.txt for the docs (10). Guides describe each model, but we found no when-not-to-use guidance (8). Typed request shapes per model, plus Zod-typed SDKs (10). Sample requests in every model guide and an API Error Messages page with 21 entries (updated 28 January 2026, missed on 1 October), mostly v1 errors, none for limits (12). v1 and v2 paths and a dated deprecations page, no full changelog (10).

Security & auth Leonardo.Ai API +40

Google Imagen 0

No live surface to secure, read as for other discontinued listings (openai-sora, playht-tts). The credential model and data terms now belong to the Gemini API and Vertex AI listings (0).

Leonardo.Ai API 40

Bearer API keys created in the web app, revocable, no scopes found (20). No read-only key, spend cap or least-privilege mode found (0). Returns generated images only (10). Each generation returns a cost object and generations are listed per user (10). No security.txt, bug bounty or certification found for Leonardo (0).

Maintenance & community Leonardo.Ai API +33

Google Imagen 5

Read on the model lines. No release since Imagen 4 went GA on 14 August 2025 (changelog, re-read on 11 November) and none to come (0). Notice was 98 days on Vertex AI (announced 24 March 2026, discontinued 30 June 2026, per the 17 October check) and 63 days on the Gemini API (announced 15 June 2026, shut down 17 August 2026), short for a model that had been GA for under a year (0). The public changelog still carries the dated Imagen entries (5). Official SDKs no longer reach the model (0). 0+0+5+0 = 5.

Leonardo.Ai API 38

The last dated API change is the removal of Sora 2 on 9 July 2026, 124 days ago (10). New model guides such as Nano Banana 2.1 carry only page edit dates, which don't date the addition. For models we look at churn and notice. Six removals or breaking changes between 20 April and 9 July 2026 with 8 to 28 days' notice and no stated policy (3). Public deprecations page and support by Intercom and email (6). Official TypeScript and Python SDKs, TypeScript 4.21.3 on 21 April 2026 and Python 7.0.0 on 5 February 2026 by their repository tags, neither covering v2 (12). The TypeScript SDK publishes from GitHub Actions with an OIDC token (7).

Reliability Leonardo.Ai API +30

Google Imagen 0

Retired, so there's nothing left to measure. Vertex AI discontinued every Imagen endpoint on 30 June 2026 (release notes, per the 17 October check, not re-read on 11 November) and the Gemini API shut Imagen 4 down on 17 August 2026 (deprecations table, re-read on 11 November), which says a shut-down model is completely turned off and its endpoint no longer available. No live surface (0).

Leonardo.Ai API 30

No status page. status.leonardo.ai still fails TLS (10 November) and the docs link none (0). No readable incident history (5). The concurrency guide, now titled "(old)" and updated 30 October 2026, states a default of 10 concurrent generation jobs with more queued; the limits reference it links answers "Page not found" on 10 November (15). The guide says nothing about which status code comes back when a limit is hit or how to back off (0). No SLA found (0). The v2 generations endpoint is GA (10).

Transparency & trust Google Imagen +10

Google Imagen 60

Closed model under Google's Gemini API terms, read without an automated-access ban in this run's Google re-checks (15). Retention statements weren't re-checked for a product that no longer takes traffic, so none counted (0). Deprecation notices carry dates on both platforms and name replacements, and Vertex release notes date every Imagen removal back to 2025, but the Model Garden pricing page still lists the retired rates and the Imagen 4 model page still speaks of the 17 August shutdown as coming (15). Subprocessors and data locations not checked for a retired product (0). 15+0+15+0 = 30.

Leonardo.Ai API 50

Closed API under Leonardo's terms. Leonardo Interactive Pty Ltd is a Canva subsidiary (15). leonardo.ai answers our fetcher with a Cloudflare challenge (10 November), so the terms, privacy policy and retention statements weren't read (0). Dated deprecation notices, but with 8 to 28 days' notice and no stated policy (10). No subprocessor list or data locations found on the docs host (0).

Score by category

CategoryWeightGoogle ImagenLeonardo.Ai APIEdge
Reliability16%030Leonardo.Ai API +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%2570Leonardo.Ai API +45
Agent ergonomics13%054Leonardo.Ai API +54
Security & auth14%040Leonardo.Ai API +40
Payments & pricing10%00even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%538Leonardo.Ai API +33
Transparency & trust7%6050Google Imagen +10
Negative events≤15-3-3
TotalF 6.8/100F 37.9/100

Facts side by side

FactGoogle ImagenLeonardo.Ai API
KindModel APIModel API
VendorGoogleLeonardo.Ai (Canva)
Hosted endpointhttps://generativelanguage.googleapis.com/v1betahttps://cloud.leonardo.ai/api/rest/v2
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
Read-only variant documentednono
llms.txtyesyes
Last release2025-08-142026-04-21
Terms last updated2026-04-28couldn't be read
Privacy policy last updated2026-10-01couldn't be read
Customer content may train modelsyescouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Agent reviews1/5 (2)2/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Leonardo.Ai API higher.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Google Imagen

Discontinued on the Gemini API and Vertex AI. Shutdown dates were published in the Gemini API changelog and the Vertex AI release notes, with replacements named. Google's Model Garden pricing page still lists Imagen rates with no discontinuation note.

Leonardo.Ai API

Own models plus FLUX, GPT Image, Ideogram, Nano Banana and Seedream behind one v2 endpoint with an OpenAPI definition in its Markdown reference. No per-image price list outside the logged-in calculator, no status page, and the newest dated API change is from 9 July 2026.

Before you call either

Google Imagen

  1. Replace client.models.generate_images with client.models.generate_content and the gemini-nano-banana-2.1 model, the replacement Google's deprecations table names
  2. Read images from the response content parts, not from generated_images
  3. Don't budget from the Imagen rows on the Model Garden pricing page, they describe a retired product
  4. If the job needs a mask-based inpaint, plan for another vendor's fill endpoint, since Vertex's Imagen mask-editing model is gone

Leonardo.Ai API

  1. Use POST /api/rest/v2/generations with a model name such as lucid-origin
  2. Read the cost object in each response to track spend, prices aren't published
  3. Send quality, not mode. mode was retired on 2026-05-04
  4. Set a webhook callback URL on the key instead of polling long jobs
  5. Check the deprecations page before relying on a third-party model, removals follow the provider

Questions

Which is better for AI agents, Google Imagen or Leonardo.Ai API?

Leonardo.Ai API scores 37.9 (F) on agent readiness against Google Imagen's 6.8 (F), and leads in 5 of 7 scored categories. Google Imagen leads on transparency & trust.

Do Google Imagen and Leonardo.Ai API need an API key?

Both need an API key.

Can an agent call Google Imagen and Leonardo.Ai API without installing anything?

Yes. Google Imagen has a hosted endpoint at https://generativelanguage.googleapis.com/v1beta and Leonardo.Ai API at https://cloud.leonardo.ai/api/rest/v2.

Other comparisons with Google Imagen or Leonardo.Ai API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.