OpenAI-compatible API. Change one line of code.
curl https://api.oriai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-your-api-key" \
-d '{
"model": "deepseek-r1",
"messages": [
{"role": "user", "content": "Hello!"}
],
"stream": true
}'from openai import OpenAI
client = OpenAI(
api_key="sk-your-oriai-key",
base_url="https://api.oriai.com/v1"
)
response = client.chat.completions.create(
model="deepseek-r1",
messages=[
{"role": "user", "content": "Explain quantum computing"}
],
stream=True
)
for chunk in response:
print(chunk.choices[0].delta.content or "", end="")| Model ID | Name | Context |
|---|---|---|
deepseek-v4-pro | DeepSeek V4 Pro | 256K |
deepseek-v4-flash | DeepSeek V4 Flash | 128K |
deepseek-r1 | DeepSeek R1 | 128K |
deepseek-coder | DeepSeek-Coder | 128K |
glm-5.2 | GLM-5.2 | 256K |
glm-5-turbo | GLM-5 Turbo | 128K |
glm-5v-turbo | GLM-5V Turbo | 128K |
qwen3.7-max | Qwen3.7 Max | 128K |
qwen3.7-plus | Qwen3.7 Plus | 128K |
qwen3.6-flash | Qwen3.6 Flash | 128K |
kimi-k2.7-code | Kimi K2.7 Code | 128K |
kimi-k2.6 | Kimi K2.6 | 128K |
minimax-m3 | MiniMax M3 | 128K |
minimax-m2.7 | MiniMax M2.7 | 128K |
Pay-as-you-go. 30% markup over upstream costs.
| Model | Input ($/M tok) | Output ($/M tok) |
|---|---|---|
deepseek-v4-pro | $0.57 | $1.13 |
deepseek-v4-flash | $0.12 | $0.23 |
deepseek-r1 | $0.72 | $2.85 |
deepseek-coder | $0.57 | $1.13 |
glm-5.2 | $1.17 | $4.00 |
glm-5-turbo | $1.56 | $5.20 |
glm-5v-turbo | $1.56 | $5.20 |
qwen3.7-max | $1.63 | $4.88 |
qwen3.7-plus | $0.42 | $1.66 |
qwen3.6-flash | $0.24 | $1.46 |
kimi-k2.7-code | $0.96 | $4.55 |
kimi-k2.6 | $0.85 | $4.43 |
minimax-m3 | $0.39 | $1.56 |
minimax-m2.7 | $0.23 | $0.94 |