New: OpenAI-compatible chat + embeddings
Affordable tokens at blazing fast speeds
Serverless GPU inference for open source models with predictable latency, simple pricing, and drop-in OpenAI APIs.
Zero cold starts Usage + rate limits OpenAI compatible
Global Infrastructure
Worldwide reach,
blazing fast inference
Distributed cloud infrastructure with an inference engine built for speed.
Integrate in seconds
Our API is fully compatible with the OpenAI SDK. Simply change the base URL and API key to switch to open-source models.
1
Get your API Key
Sign up and generate a key in the dashboard.
2
Configure Client
Point your existing SDK to EmberCloud endpoints.
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.embercloud.ai/v1", api_key="ember_sk_..." ) completion = client.chat.completions.create( model="glm-4.7", messages=[ {"role": "user", "content": "Hello World!"} ] ) print(completion.choices[0].message.content)
Model Library
Production-ready models
Access top-tier open models through a unified, OpenAI-compatible API.
New
Chat
GLM 5
745B MoE 203K ctx
$0.720 in · $2.30 out / 1M
View pricing
Chat
GLM 4.7
355B MoE 200K ctx
$0.380 in · $1.98 out / 1M
View pricing
Fast
Fast
GLM 4.7 Flash
30B MoE 200K ctx
$0.060 in · $0.400 out / 1M
View pricing
Chat
GLM 4.5
355B MoE 131K ctx
$0.600 in · $2.20 out / 1M
View pricing
New
Chat
GLM 5
745B MoE 203K ctx
$0.720 in · $2.30 out / 1M
View pricing
Chat
GLM 4.7
355B MoE 200K ctx
$0.380 in · $1.98 out / 1M
View pricing
Fast
Fast
GLM 4.7 Flash
30B MoE 200K ctx
$0.060 in · $0.400 out / 1M
View pricing
Chat
GLM 4.5
355B MoE 131K ctx
$0.600 in · $2.20 out / 1M
View pricing
Value
Chat
GLM 4.5 Air
131K ctx
$0.130 in · $0.850 out / 1M
View pricing
Value
Code
Qwen3 Coder Next
262K ctx
$0.108 in · $0.675 out / 1M
View pricing
Chat
Kimi K2.5
262K ctx
$0.405 in · $1.98 out / 1M
View pricing
Chat
MiniMax M2.5
196K ctx
$0.200 in · $1.20 out / 1M
View pricing
Value
Chat
GLM 4.5 Air
131K ctx
$0.130 in · $0.850 out / 1M
View pricing
Value
Code
Qwen3 Coder Next
262K ctx
$0.108 in · $0.675 out / 1M
View pricing
Chat
Kimi K2.5
262K ctx
$0.405 in · $1.98 out / 1M
View pricing
Chat
MiniMax M2.5
196K ctx
$0.200 in · $1.20 out / 1M
View pricing
Transparent Pricing
Flexible token pricing
Pay only for what you generate. No idle costs.
| Model | Context | Input | Output | Cached Input |
|---|---|---|---|---|
 GLM 5New | 203K | $0.720 / 1M | $2.30 / 1M | $0.144 / 1M |
| GLM 4.7 | 200K | $0.380 / 1M | $1.98 / 1M | $0.190 / 1M |
| GLM 4.7 FlashFast | 200K | $0.060 / 1M | $0.400 / 1M | $0.010 / 1M |
| GLM 4.5 | 131K | $0.600 / 1M | $2.20 / 1M | $0.110 / 1M |
| GLM 4.5 AirValue | 131K | $0.130 / 1M | $0.850 / 1M | $0.025 / 1M |
 Qwen3 Coder NextValue | 262K | $0.108 / 1M | $0.675 / 1M | $0.060 / 1M |
 Kimi K2.5 | 262K | $0.405 / 1M | $1.98 / 1M | $0.225 / 1M |
 MiniMax M2.5 | 196K | $0.200 / 1M | $1.20 / 1M | $0.040 / 1M |