Integrations

Anthropic SDK & Claude Code

Use DEVUP AI models with the Anthropic Messages API, Claude Code, and the Anthropic SDK.

DEVUP AI exposes an Anthropic-compatible Messages API. This means tools that target the Anthropic API — Claude Code, the Anthropic Python and TypeScript SDKs, and any framework with an Anthropic adapter — can point at DEVUP AI and use open-source models.

Endpoint

bash

https://api.devupai.com/anthropic

Two endpoints are available:

POST /anthropic/v1/messages	Create a message (chat completion)
POST /anthropic/v1/messages/count_tokens	Count tokens for a message request

Authentication

Both standard Anthropic authentication methods are supported:

Authorization	`Bearer $DEVUP_API_KEY`
x-api-key	`$DEVUP_API_KEY`

You can also pass anthropic-version and anthropic-beta headers as needed.

Using the Anthropic SDK

pip install anthropic

import anthropic

client = anthropic.Anthropic(
    base_url="https://api.devupai.com/anthropic",
    api_key="$DEVUP_API_KEY",
)

message = client.messages.create(
    model="deepseek-ai/DeepSeek-V3",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(message.content[0].text)

Using with Claude Code

Claude Code can use DEVUP AI as its backend. To keep your normal Claude Code setup untouched, add a dedicated shell function to your ~/.bashrc or ~/.zshrc:

bash

devupai() {
  export ANTHROPIC_BASE_URL="https://api.devupai.com/anthropic"
  export ANTHROPIC_AUTH_TOKEN=$DEVUP_API_KEY
  export ANTHROPIC_MODEL="deepseek-ai/DeepSeek-V3"
  claude "$@"
}

Then run devupai instead of claude to launch Claude Code via DEVUP AI. Your regular claude command stays unchanged.

Model override environment variables

Claude Code uses model aliases (opus, sonnet, haiku) internally. You can remap each alias to a DEVUP AI model using these environment variables:

ANTHROPIC_MODEL	`deepseek-ai/DeepSeek-V3`
ANTHROPIC_DEFAULT_OPUS_MODEL	`deepseek-ai/DeepSeek-R1`
ANTHROPIC_DEFAULT_SONNET_MODEL	`deepseek-ai/DeepSeek-V3`
ANTHROPIC_DEFAULT_HAIKU_MODEL	`Qwen/Qwen3-30B-A3B`
CLAUDE_CODE_SUBAGENT_MODEL	`Qwen/Qwen3-30B-A3B`

A more complete example with all overrides:

bash

devupai() {
  export ANTHROPIC_BASE_URL="https://api.devupai.com/anthropic"
  export ANTHROPIC_AUTH_TOKEN=$DEVUP_API_KEY
  export ANTHROPIC_MODEL="deepseek-ai/DeepSeek-V3"
  export ANTHROPIC_DEFAULT_OPUS_MODEL="deepseek-ai/DeepSeek-R1"
  export ANTHROPIC_DEFAULT_SONNET_MODEL="deepseek-ai/DeepSeek-V3"
  export ANTHROPIC_DEFAULT_HAIKU_MODEL="Qwen/Qwen3-30B-A3B"
  export CLAUDE_CODE_SUBAGENT_MODEL="Qwen/Qwen3-30B-A3B"
  export CLAUDE_CODE_MAX_OUTPUT_TOKENS=16384
  claude "$@"
}

ANTHROPIC_DEFAULT_HAIKU_MODEL is used for lightweight background tasks like tab completions and commit messages. Pick a fast, cheap model here to keep costs low. The older ANTHROPIC_SMALL_FAST_MODEL variable is deprecated — use ANTHROPIC_DEFAULT_HAIKU_MODEL instead.

Streaming

Streaming works the same as the Anthropic API — use stream=True (Python) or stream: true (JS/cURL):

python

with client.messages.stream(
    model="deepseek-ai/DeepSeek-V3",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Write a short poem about open source."}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

Token counting

bash

curl "https://api.devupai.com/anthropic/v1/messages/count_tokens" \
  -H "Content-Type: application/json" \
  -H "x-api-key: $DEVUP_API_KEY" \
  -d '{
      "model": "deepseek-ai/DeepSeek-V3",
      "messages": [{"role": "user", "content": "Hello, how are you?"}]
    }'

Notes

You are running open-source models via the Anthropic protocol, not Anthropic's Claude models.
Model names use DEVUP AI identifiers (e.g., deepseek-ai/DeepSeek-V3), not Anthropic model names.
Not all Anthropic-specific features may be supported. Standard message creation, streaming, and token counting work as expected.

Chat Completions

Use the OpenAI-compatible API instead.

Authentication

API keys and scoped JWTs.

Native API

AutoGen