Start in 60 seconds
Three steps from sign-up to your first API call.
1
Get your free API key
Sign up in seconds. No credit card required. Your key is ready instantly.
2
Call any model
Use the OpenAI SDK. Just change the base URL. No new code to write.
3
Track costs in your dashboard
Every request is logged with cost. See your spend, set budgets, get alerts.
Models available today
All accessible through one OpenAI-compatible endpoint.
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| gemini-3.5-flashGemini 3.5 Flash | $1.50 | $9.00 | 1,048.576K |
| gemini-3.5-flash-liteGemini 3.5 Flash Lite | $0.30 | $2.50 | 1,048.576K |
Moonshot
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| kimi-3Kimi K3 | $0.60 | $2.50 | 262.144K |
OpenAI
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| gpt-oss-120bGPT OSS 120B | $0.35 | $1.40 | 131.072K |
| gpt-oss-20bGPT OSS 20B | $0.10 | $0.40 | 131.072K |
MiniMax
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| minimax-m3MiniMax M3 | $0.30 | $1.20 | 1,000K |
Zhipu
| Model | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| glm-5.2GLM 5.2 | $0.30 | $1.20 | 131.072K |
Why BroadComms Gateway
One endpoint, every model
Kimi, Gemini, GPT-OSS, MiniMax, GLM. All behind a single OpenAI-compatible API.
Prices we control
Flat per-model pricing. No provider confusion. The price you see is the price you pay.
Automatic failover
If a provider goes down, your request routes to a backup automatically.
Cost visibility from day one
Per-request cost logging, budget alerts, and usage analytics on day one.
One line to switch
Already using the OpenAI SDK? Change the base URL and your API key.
from openai import OpenAI
client = OpenAI(
api_key="sk-bc-YOUR_KEY",
base_url="https://api.broadcomms.net/v1"
)
# Everything else stays the same
response = client.chat.completions.create(
model="kimi-3",
messages=[{"role": "user", "content": "Hello!"}]
)