Guide
OpenAI-compatible API with one key
Keep the OpenAI SDK and change two values: base_url and the key. The model is a published LLMcode profile, priced per 1M tokens.
Updated
What is compatible
The gateway accepts POST /v1/chat/completions, POST /v1/responses, POST /v1/embeddings and GET /v1/models. Authentication is the same Bearer token the OpenAI SDK already sends.
Streaming works for chat completions. Responses with stream: true returns 400 in this version — check the limitation before you rely on it.
- Base URL: https://llmcode.io/v1
- Key: sk-llmcode-…, shown once
- Model: a published profile from /models
Billing in plain terms
You prepay in USD, minimum $10, and the balance is spent on actual token usage. There is no subscription and no auto-charge.
Each request is priced from the catalog: input, output and, when the provider reports it, cached input. The applied price is stored in the request journal.
What this is not
This is not an OpenAI account and not a promise of a specific network route. Models are served through partner APIs behind a compatible interface.
Internal provider names and supplier costs are not exposed. Only published profiles and the sale price are public.
Connect
curl https://llmcode.io/v1/chat/completions \
-H "Authorization: Bearer $LLMCODE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://llmcode.io/v1",
api_key=os.environ["LLMCODE_API_KEY"],
)
reply = client.chat.completions.create(
model="deepseek-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)Published model prices
USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.
| Model | Input | Output | Cache |
|---|---|---|---|
| Claude Opus 5.5 | $2.70 | $8.00 | $0.14 |
| DeepSeek Flash | $0.50 | $2.00 | $0.01 |
| Claude Sonnet 5.5 | $1.33 | $6.67 | $0.07 |
| DeepSeek V4 Pro | $2.20 | $6.60 | $0.07 |
Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.
Questions
Do I need to change my code?
Usually no: set base_url to https://llmcode.io/v1 and replace the API key. The model must be a published profile.
Is streaming supported?
Yes for /v1/chat/completions and /v1/messages. Responses with stream: true is not supported in this version.
How much does it cost?
The price is per 1M input and output tokens for the chosen model. See the live table on this page; there is no monthly fee.
Can I limit a key?
Yes: a spend limit in UT, an IP allowlist and an expiry date per key. Up to 20 active keys per account.