API
A drop-in OpenAI-compatible API — point any OpenAI SDK at our base URL and change two lines. Same uncensored models you use in chat, pay-per-token, no subscription, and no sign-up: your key is your account. Compete-on-price routing means you always hit the cheapest live provider.
Base URL
https://dllmnetwork.com/v1
Auth header: Authorization: Bearer YOUR_KEY. Standard OpenAI Chat Completions API — /v1/chat/completions, /v1/models, streaming and all.
Quickstart
cURL
curl https://dllmnetwork.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bria-bg-remover",
"messages": [{"role": "user", "content": "Hello"}]
}'Python (OpenAI SDK)
from openai import OpenAI
client = OpenAI(
base_url="https://dllmnetwork.com/v1",
api_key="YOUR_KEY",
)
r = client.chat.completions.create(
model="bria-bg-remover",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)JavaScript / Node (openai)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://dllmnetwork.com/v1",
apiKey: "YOUR_KEY",
});
const r = await client.chat.completions.create({
model: "bria-bg-remover",
messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);Streaming
Set stream: true for token-by-token SSE (data: chunks ending in data: [DONE]) — same as OpenAI's streaming.
curl https://dllmnetwork.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "bria-bg-remover", "messages": [{"role":"user","content":"Hi"}], "stream": true}'Models & pricing
GET /v1/models returns the live catalog. Prices are USD per 1M tokens (cheapest live provider) — see full pricing.
| Model ID | $/1M in | $/1M out | $/image |
|---|---|---|---|
bria-bg-remover | — | — | $0.036 |
chroma | — | — | $0.012 |
claude-opus-4.6 | $6.6 | $33 | — |
claude-opus-4.8 | $6.6 | $33 | — |
claude-sonnet-4.6 | $3.96 | $19.8 | — |
deepseek-v3.2 | $0.396 | $0.576 | — |
deepseek-v4-pro | $1.815 | $3.6311 | — |
flux-2-max | — | — | $0.099 |
flux-2-pro | — | — | $0.044 |
gemini-3.5-flash | $1.705 | $10.395 | — |
gemma-4-26b-a4b | $0.156 | $0.48 | — |
gemma-4-26b-uncensored-tee | $0.228 | $1.056 | — |
gemma-4-31b | $0.144 | $0.432 | — |
gemma-4-31b-tee | $0.1668 | $0.516 | — |
gemma-4-uncensored-venice | $0.195 | $0.6 | — |
glm-4.7 | $0.66 | $3.18 | — |
glm-5.1-e2ee | $1.32 | $4.98 | — |
glm-5.2 | $1.68 | $5.28 | — |
gpt-5.5 | $6.875 | $41.25 | — |
gpt-image-1-5 | — | — | $0.286 |
gpt-image-2 | — | — | $0.297 |
grok-4.3 | $1.562 | $3.113 | — |
grok-imagine-image | — | — | $0.044 |
grok-imagine-image-quality | — | — | $0.088 |
hunyuan-image-v3 | — | — | $0.099 |
ideogram-v4 | — | — | $0.165 |
imagineart-1.5-pro | — | — | $0.066 |
kimi-k2.6 | $0.9 | $4.2 | — |
kimi-k2.7-code | $0.9 | $4.2 | — |
krea-v2-large | — | — | $0.077 |
krea-v2-medium | — | — | $0.044 |
lustify-sdxl | — | — | $0.012 |
lustify-v7 | — | — | $0.012 |
lustify-v8 | — | — | $0.012 |
minimax-m3 | $0.36 | $1.44 | — |
nano-banana-2 | — | — | $0.11 |
nano-banana-pro | — | — | $0.198 |
qwen-3.6-plus-uncensored | $0.75 | $4.5 | — |
qwen-3.7-plus | $0.6 | $2.4 | — |
qwen-image | — | — | $0.036 |
qwen-image-2 | — | — | $0.055 |
qwen-image-2-pro | — | — | $0.11 |
recraft-v4 | — | — | $0.055 |
recraft-v4-pro | — | — | $0.319 |
seedream-v4 | — | — | $0.055 |
seedream-v5-lite | — | — | $0.055 |
venice-sd35 | — | — | $0.012 |
wai-Illustrious | — | — | $0.012 |
wan-2-7-pro-text-to-image | — | — | $0.1031 |
wan-2-7-text-to-image | — | — | $0.045 |
z-image-turbo | — | — | $0.012 |
Errors
| Code | Meaning |
|---|---|
| 401 | missing / invalid key |
| 402 | out of credits — top up |
| 429 | rate-limited — back off (see Retry-After) |
400 content_policy | the one hard rule: no sexual content involving minors |
We don't log API prompts or responses — only token counts, for billing. (Saved web-chat history is stored encrypted; we can't read it.)