Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.raziel.fun/llms.txt

Use this file to discover all available pages before exploring further.

The Raziel gateway exposes two protocol surfaces: a drop-in replacement for the Anthropic Messages API and an OpenAI-compatible chat completions endpoint. Both use your rz_live_… key for authentication and support streaming.

​
Anthropic-compatible endpoint

Send requests to https://raziel.fun/gateway/v1/messages in the same format you would send them to https://api.anthropic.com/v1/messages. The gateway forwards the request body unchanged to a live provider and returns the response in the same Anthropic shape.
When using the razi claude command, requests go through a local proxy at localhost:3099. The raziel.fun domain never appears in Claude Code’s network traffic.

​
Request

POST https://raziel.fun/gateway/v1/messages
Authorization: Bearer rz_live_xxxxxxxxxxxx
Content-Type: application/json
anthropic-version: 2023-06-01

{
  "model": "claude-sonnet-4-6",
  "max_tokens": 1024,
  "messages": [
    { "role": "user", "content": "Hello" }
  ]
}

​
Parameters

​
model
string
required
The model to use. See available models below.
​
messages
array
required
Array of message objects with role (user or assistant) and content.
​
max_tokens
integer
required
Maximum number of tokens to generate in the response.
​
stream
boolean
Set to true to receive a server-sent events stream. The gateway passes streaming through transparently.
​
system
string
System prompt passed directly to the model.
​
temperature
number
Sampling temperature between 0 and 1.
​
tools
array
Tool definitions for function calling. Passed through to the provider unchanged.

​
Example: streaming request

curl https://raziel.fun/gateway/v1/messages \
  -H "Authorization: Bearer rz_live_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 512,
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

​
OpenAI-compatible endpoint

The gateway also speaks the OpenAI chat completions format at https://raziel.fun/gateway/openai/v1. Use it with any client that accepts a custom base URL — the OpenAI SDK, Hermes, Continue, LibreChat, and others.

​
Endpoints

MethodPathDescription
POST/gateway/openai/v1/chat/completionsCreate a chat completion
GET/gateway/openai/v1/modelsList available models

​
Request

POST https://raziel.fun/gateway/openai/v1/chat/completions
Authorization: Bearer rz_live_xxxxxxxxxxxx
Content-Type: application/json

{
  "model": "claude-sonnet-4-6",
  "messages": [
    { "role": "user", "content": "Hello" }
  ],
  "max_tokens": 512
}

​
Parameters

​
model
string
required
The model identifier. See available models below.
​
messages
array
required
Array of message objects with role and content.
​
max_tokens
integer
Maximum number of tokens to generate.
​
temperature
number
Sampling temperature between 0 and 2.
​
stream
boolean
Set to true to receive a server-sent events stream.
​
tools
array
OpenAI-format tool definitions for function calling.
​
tool_choice
string | object
Tool selection strategy: "auto", "none", "required", or a specific tool object.
​
stop
string | array
Up to 4 sequences where the API will stop generating.
​
top_p
number
Nucleus sampling parameter.
The following fields are accepted but silently ignored: logprobs, n, response_format, presence_penalty, frequency_penalty, seed. Requests that include them will succeed, but these parameters have no effect.

​
Example

from openai import OpenAI

client = OpenAI(
    base_url="https://raziel.fun/gateway/openai/v1",
    api_key="rz_live_xxxxxxxxxxxx",
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

​
Available models

Model IDDescription
claude-opus-4-7Claude Opus 4.7 — most capable
claude-sonnet-4-6Claude Sonnet 4.6 — balanced performance and speed
claude-haiku-4-5-20251001Claude Haiku 4.5 — fastest responses
Use GET /gateway/openai/v1/models to retrieve the current model list programmatically.

​
Authentication

Both endpoints use the same Authorization: Bearer scheme. 
Authorization: Bearer rz_live_xxxxxxxxxxxx
Alternatively, for the Anthropic-compatible endpoint you can pass your key as x-api-key: 
x-api-key: rz_live_xxxxxxxxxxxx
Issue and manage keys from Customer → API Keys in the dashboard. Keys are shown in full only once at creation — store them immediately.