Skip to main content
POST
  • Protocol: OpenAI Chat Completions (POST /v1/chat/completions)
  • Shared contract for all Claude ids below; only body model changes
  • Synchronous by default; stream: true for SSE

Available models

Base URL: https://api.omnimux.ai

Authorizations

Authorization
string
header
required

API key auth. Header: Authorization: Bearer sk-... (create keys in the OmniMux console).

Body

application/json
model
enum<string>
default:claude-fable-5
required

Model id for this brand on OmniMux. Same request/response shape for all ids below; only the model value changes.

Available options:
claude-fable-5,
claude-haiku-4-5,
claude-opus-4-6,
claude-opus-4-7,
claude-opus-4-8,
claude-opus-5,
claude-sonnet-4-6,
claude-sonnet-5
Example:

"claude-fable-5"

messages
object[]
required

对话消息列表

temperature
number
default:1

采样温度

Required range: 0 <= x <= 2
top_p
number
default:1

核采样参数

Required range: 0 <= x <= 1
n
integer
default:1

生成数量

Required range: x >= 1
stream
boolean
default:false

是否流式响应

stream_options
object
stop

停止序列

max_tokens
integer

最大生成 Token 数

max_completion_tokens
integer

最大补全 Token 数

presence_penalty
number
default:0
Required range: -2 <= x <= 2
frequency_penalty
number
default:0
Required range: -2 <= x <= 2
logit_bias
object
user
string
tools
object[]
tool_choice
Available options:
none,
auto,
required
response_format
object
seed
integer
reasoning_effort
enum<string>

推理强度 (用于支持推理的模型)

Available options:
low,
medium,
high
modalities
enum<string>[]
Available options:
text,
audio
audio
object

Response

Chat completion successful

id
string
object
string
Example:

"chat.completion"

created
integer
model
string
choices
object[]
usage
object
system_fingerprint
string