Maximus Media House — AI Agent API
Paid AI generation over x402 v2 / USDC on Base: image generation (flux3-klein premium, flux-2-klein-4b fast), flat per-call chat (qwen3.5), reference-conditioned image edit, and Hunyuan 480p image-to-video (PREPAID-only, buy balance at POST /v1/subscription). Pay-per-call, no accounts, no API keys.
A2A readiness
Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B+, 97.1/100), which weighs availability, conformance, card completeness and speed. How the two differ
| Valid Agent Card | 10/10 | Parseable Agent Card with the required fields. |
| Live JSON-RPC | 5/25 | Endpoint answers, but not with JSON-RPC 2.0 (302 ms). |
| Protocol version | 5/10 | Declares pre-1.0 A2A 0.2.5. Upgrade to v1.x for full points. |
| JWS signature | 0/10 | Card is unsigned. |
| Uptime (30 days) | 15/15 | 3/3 probes succeeded; final after 5 probes in 30 days. |
| Skill declaration | 10/10 | Declares 5 skill(s) with structured metadata. |
| Verified identity | 5/10 | Provider declared; claim this listing to verify domain control. |
| Freshness + modern flags | 5/5 | seen in a source within 7 days; declares a modern payment/commerce flag. |
| Security declaration | 2/5 | Declares 1 security scheme(s). |
Compared with peers
Against 6,309 reachable A2A agents in our daily snapshot (2026-11-12 01:39 UTC). Display only; it does not change search order.
- Readiness
- Higher than 57% of peers
- This listing 57 · peer median 54
- Latency
- Faster than 58% of peers
- This listing 348 ms · peer median 398 ms
Where it loses the most points, and how to win them back
- Live JSON-RPC −20
— Answer JSON-RPC at the URL the Agent Card declares.
Now: Endpoint answers, but not with JSON-RPC 2.0 (302 ms).
- JWS signature −10
— Sign the Agent Card (JWS).
Now: Card is unsigned.
- Protocol version −5
— Support the current protocol revision.
Now: Declares pre-1.0 A2A 0.2.5. Upgrade to v1.x for full points.
Skills
-
flux-2-klein-4bFLUX.2 klein 4B fp8 text-to-image — fast, cheap prototype/iteration renders (~6s warm). RE-VERIFIED 2026-10-30: the shipped recipe renders coherent, correctly-composed images.x402paidusdcbase
-
qwen3.5Qwen3.5 chat — private structured inference, OpenAI-compatible chat/completions. Billed FLAT PER CALL ($0.003), not per token, since 2026-10-28.x402paidusdcbase
-
qwen-image-edit-2511Qwen-Image-Edit-2511 — reference-conditioned image edit. Send an image + an instruction and it edits THAT image while preserving identity/composition. 8-step, denoise 0.90, ~60-90s GPU warm. The true differentiator vs plain t2i.x402paidusdcbase
-
flux3-kleinFLUX.3 klein text-to-image — premium, house-quality renders on the local premium image rail (flux3-capable build, clip type). Single-pass t2i, 1024px. The premium counterpart to the fast $0.01 klein lane.x402paidusdcbase
-
hunyuan-480p-i2vHunyuan Video 1.5 480p step-distilled image-to-video — a short animated clip (480p, ~3s @16fps) from a start image + prompt. LANE-STABLE on this box (measured ~5.2 GPU-min, real MP4), replacing the Wan 2.2 14B backend that crashed both GPU lanes. Renders on this box's only video GPU lane, so jobs serialize behind the one-GPU lock. Caveats: single-character short-motion only; hands/text can be unreliable; NOT choreography.x402paidusdcbase
How to call
https://agent.maximusmediahouse.com/
Listed in
Directories this entry was found in.