▸ CDN-NATIVE▸ STATELESS▸ ZERO-SERVER-COMPUTE▸ WEBGPU-ACCELERATED▸ NEMOTRON-3-ULTRA-550B▸ EDGE-CACHED-FOREVER▸ OPEN-API▸ NO-AUTH▸ NO-RATE-LIMIT▸ DECENTRALIZED▸ CDN-NATIVE▸ STATELESS▸ ZERO-SERVER-COMPUTE▸ WEBGPU-ACCELERATED▸ NEMOTRON-3-ULTRA-550B▸ EDGE-CACHED-FOREVER▸ OPEN-API▸ NO-AUTH▸ NO-RATE-LIMIT▸ DECENTRALIZED
v1.0.0-edge · 18 edge regions live

The server is anavigator.Your browser is the renderer.

CoreAgents.app is a CDN-native, stateless, decentralized image synthesis platform. We use Nemotron-3-Ultra-550B only to optimize prompts into JSON specs. The heavy diffusion compute runs on your GPU via WebGPU. Vercel Edge CDN caches every response for a year — zero function invocations, zero API cost, zero rate limits.

Cache TTL
31536000s
Server compute
0.00 GFLOPs
24h cache hit-rate
94.2%
Bandwidth cost
$0.00
Status
operational
Edge regions
Avg nav latency
24h cache hit
24h images
24h server cost
Chat · Navigator (spec only)
coreagents
AI: プロンプトを入力してください。最小コストで navigator spec を生成し、その結果(最適化プロンプト/パレット)を返します。
※ このチャットは pixels を返さず、navigator spec(optimized_prompt / palette)だけを返します。
02 · ARCHITECTURE

Nine steps. Zero pixels cross our servers.

Every other image-gen API is a server-heavy pipeline: prompt in → GPU farm → image out → bandwidth bill. CoreAgents inverts this. The server is a thin navigation layer cached at the edge; the user's browser does all the heavy lifting via WebGPU.

01

GET /api/v1/navigate

Client sends a single GET request with ?prompt=...&style=...&aspect_ratio=...&seed=...

02

Edge CDN Lookup

Vercel's Edge Network hashes the normalized query string. Equivalent prompts collapse to the same cache entry.

03a

Cache HIT → instant JSON

If cached, return immediately. ZERO function invocations, ZERO Nemotron calls, ZERO latency.

03b

Cache MISS → Edge Function

On miss, the Edge Function calls Nemotron-3-Ultra-550B to optimize the prompt into a compact JSON spec.

04

Nemotron Navigator

Nemotron returns only {optimized_prompt, palette, tags, seed, guidance, steps}. NO pixels. NO heavy compute.

05

CDN Caches Forever

Response ships with Cache-Control: s-maxage=31536000. Cached at 18 edge regions for a year.

06

Browser Downloads Model

Browser fetches quantized model directly from HuggingFace CDN. Vercel bandwidth consumed: 0 bytes.

07

WebGPU Synthesis

Browser runs multi-step diffusion locally on the user's GPU. 4-step turbo takes ~600ms.

08

Canvas Composite

Final latent grid composited to <canvas>. Serverless from here on. The image lives only in the user's browser.

Why this wins · CoreAgents vs. everyone else

DimensionTraditional API (e.g. OpenAI Images)CoreAgents.app
Server computeGPU farm, $$/image$0.00 — browser GPU
Per-image cost$0.02 – $0.17$0.00 after first cache miss
Rate limit5 – 50 req/minUnlimited (CDN absorbs)
Auth requiredAPI key, billingNone
Latency (warm)2 – 8 seconds<50ms cache hit
DDoS resistanceRate limiter, WAFCDN IS the defense
BandwidthServer pays egressHuggingFace pays egress
Horizontal scaleProvision GPUsInfinite (it's just JSON)
04 · NAVIGATOR

Nemotron-3-Ultra-550B doesn't draw. It navigates.

Running a 550-billion-parameter model on every image request would bankrupt any operator. CoreAgents uses Nemotron exclusively as a latent-space navigator: it receives your prompt and returns only a compact JSON spec — expanded tags, palette, composition hints, lighting direction, and a deterministic embedding seed. The actual pixel synthesis happens on your GPU, not ours.

Because the navigator output is deterministic and CDN-cached, we only pay for the first request for any given canonical prompt. Every subsequent request — from anyone, anywhere — hits the edge and costs nothing. We default to OpenRouter's free tier (nvidia/nemotron-3-ultra-550b-a55b:free, 1M-token context, $0), so the navigator itself runs at literally zero cost.

Prompt expansion

Nemotron rewrites your prompt into a richer tag list semantically aligned with the style preset.

Negative prompts

Automatically generated to suppress common failure modes (blur, artifacts, extra limbs).

Palette extraction

Returns 4–6 hex colors tuned to the style. The WebGPU shader quantizes output to this palette.

Composition & lighting tags

Drives focal-point placement and key/rim/fill light angles in the WGSL compute shader.

Input
"a lonely lighthouse on a stormy cliff at dusk"
Nemotron-3-Ultra-550B
~412ms · 600 tokens
role: latent-space navigator
output: JSON spec only — no pixels
// navigator output
{
  "optimized_prompt": "lone lighthouse,
    storm cliff, cyberpunk neon…",
  "palette": ["#ff2d92","#9eff00",
              "#0a0a0a","#ffd400"],
  "composition_tags": [
    "rule-of-thirds",
    "focal-asymmetry"
  ],
  "lighting_tags": [
    "rim-light","key-light-45deg"
  ],
  "seed": 3174268491,
  "guidance": 7.5,
  "steps": 4
}
Your browser · WebGPU
role: heavy-lift renderer
compute: local GPU · 4-step diffusion · ~600ms
03 · API

A single GET endpoint. No auth. No SDK.

The entire public API is one URL. Every parameter lives in the query string, so requests are cacheable by every CDN on earth. Curl it, fetch it, drop it into a Python script — no keys, no billing, no rate limits.

GET /api/v1/navigateStateless

Returns a JSON navigation spec for the browser-side WebGPU engine. Cached at the edge for one year — equivalent prompts collapse to the same cache entry automatically.

Parameters

promptstringrequired

The natural-language prompt. Normalized: lowercased, articles removed, tokens sorted. Equivalent prompts share a cache entry.

styleenumdefault: photoreal

One of: photoreal, anime, cyberpunk, low-poly, watercolor, oil, ink, vaporwave, brutalism, noir.

aspect_ratioenumdefault: 1:1

One of: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 3:2, 2:3.

stepsintegerdefault: 4

Diffusion steps (1–8). Lower = faster, higher = sharper. 4 is the turbo sweet spot.

guidancefloatdefault: 7.5

Classifier-free guidance scale (0.1–12.0). Higher = more prompt-adherent, lower = more creative.

seedintegerdefault: auto

Deterministic seed. If omitted, derived from the prompt hash — same prompt = same seed.

modelenumdefault: flux-schnell-w4

Quantized model id: sd-turbo-w4, sdxl-turbo-w4, flux-schnell-w4, kandinsky-3-w4.

# Basic call — returns the navigator JSON spec
curl "https://coreagents.app/api/v1/navigate?prompt=a%20lonely%20lighthouse%20on%20a%20stormy%20cliff&style=cyberpunk&aspect_ratio=16:9"

# Response headers (note the CDN cache directives):
#   X-CoreAgents-Hash: a3f7b2c1
#   X-CoreAgents-Cache: MISS
#   Cache-Control: public, max-age=86400, s-maxage=31536000, immutable

# Repeat the same call → X-CoreAgents-Cache: HIT, served from edge in <50ms

Try it

DMCA

著作権に関する問い合わせ窓口と対応ポリシーをこのセクションに整理します。