Anthropic-compatible streaming

Endpoint: POST /api/anthropic/v1/messages

This endpoint accepts Anthropic Messages API payloads and streams Anthropic SSE events (message_start, content_block_start, content_block_delta, message_delta, message_stop). It is compatible with tools like Claude Code.

Note: You can also call OpenAI models through this Anthropic-compatible surface; the request must still follow Anthropic message shapes. See Cross‑provider compatibility.

Request schema

model (string) – required
messages (array) – required, Anthropic-style content blocks are supported (text, image, tool_use, tool_result)
stream (boolean) – optional, must be boolean
max_tokens (int > 0) – required by Anthropic models
temperature (0..1), top_p (0..1), top_k (int > 0)
stop_sequences (string[]), metadata (object)
thinking (object), cache_control (object)
tool_choice (string | object), tools (array)
parallel_tool_calls (boolean)

Media sources

Images: { type: "image", source: { type: "base64", media_type, data } } is preferred. We also accept source: { type: "url", url } and will embed as base64 internally when needed.
PDFs: { type: "document", source: { type: "base64", media_type: "application/pdf", data } } is supported. If source.url is provided, we fetch-and-embed the PDF as base64.
Text documents: { type: "document", source: { type: "text", media_type: "text/plain", data } } is supported. If source.url points to text, we fetch-and-embed it as inline text.
Files API references: { type: "document", source: { type: "file", file_id } } is supported. See Files API below.

Invalid shapes or incompatible values return HTTP 400 with a descriptive error.

Headers

x-api-key: $API_KEY or Authorization: Bearer $API_KEY
anthropic-version: 2023-06-01
Optional betas: set anthropic-beta: token1, token2 and/or body {"betas":["token1","token2"]}.

cURL (streaming)

curl -N -X POST "https://api.kushrouter.com/api/anthropic/v1/messages" \
  -H "x-api-key: $API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5-20250929",
    "messages": [{"role":"user","content":[{"type":"text","text":"Write a haiku about routers"}]}],
    "max_tokens": 256,
    "stream": true
  }'

Streaming frames

Events are emitted with explicit event: names per Anthropic spec. Example sequence:

event: message_start
data: {"type":"message_start","message":{...}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text"}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"..."}}

event: message_delta
data: {"type":"message_delta","delta":{}} 

event: message_stop
data: {"type":"message_stop"}

Tool streaming examples

Server tool use streams as content blocks. Tool arguments may be delivered incrementally via input_json_delta.

event: content_block_start
data: {"type":"content_block_start","index":1,"content_block":{"type":"server_tool_use","id":"srvtoolu_01","name":"get_weather"}}

event: content_block_delta
data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"{\"city\":\"Bos"}}

event: content_block_delta
data: {"type":"content_block_delta","index":1,"delta":{"type":"input_json_delta","partial_json":"ton\"}"}}

event: content_block_stop
data: {"type":"content_block_stop","index":1}

event: content_block_start
data: {"type":"content_block_start","index":2,"content_block":{"type":"tool_result","tool_use_id":"srvtoolu_01","content":[{"type":"text","text":"{\"tempC\": 23}"}]}}

event: content_block_stop
data: {"type":"content_block_stop","index":2}

Tool controls

tool_choice: 'auto' | 'none' | { type: "tool", name } | { type: "function", function: { name } }
parallel_tool_calls (boolean): when false, we disable parallel tool use upstream.
pause_on_call_tools_start (boolean): causes the assistant to pause before tool execution so you can approve; resume by sending tool_result content.

Errors

400 – invalid JSON or unknown/unsupported parameters
401 – missing or invalid API key
413 – payload too large
429 – rate limit exceeded (key or IP)
5xx – transient errors

Post-stream usage

After a stream finishes, fetch token usage and metadata by generation ID (the message.id from message_start).