Anthropic-Compatible API

sglang serve \
    --model-path zai-org/GLM-5.2-FP8 \
    --tp 8 \
    --speculative-algorithm EAGLE \
    --speculative-num-steps 5 \
    --speculative-eagle-topk 1 \
    --speculative-num-draft-tokens 6 \
    --reasoning-parser glm45 \
    --tool-call-parser glm47 \
    --host 0.0.0.0 \
    --port 30000

from anthropic import Anthropic

client = Anthropic(
    base_url="http://127.0.0.1:30000",
    api_key="EMPTY",  # SGLang does not require a real key by default
)

message = client.messages.create(
    model="zai-org/GLM-5.2-FP8",
    max_tokens=512,
    messages=[{"role": "user", "content": "List 3 countries and their capitals."}],
)
# A reasoning model may emit a `thinking` block before the `text` block —
# pick the text block rather than assuming content[0].
print(next(b.text for b in message.content if b.type == "text"))

Here are 3 countries and their capitals:

1. **France** - Paris
2. **Japan** - Tokyo
3. **Brazil** - Brasília

with client.messages.stream(
    model="zai-org/GLM-5.2-FP8",
    max_tokens=512,
    messages=[{"role": "user", "content": "Say this is a test"}],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

This is a test.

message = client.messages.create(
    model="zai-org/GLM-5.2-FP8",
    max_tokens=512,
    system="You are a helpful assistant that answers concisely.",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(next(b.text for b in message.content if b.type == "text"))

The capital of France is Paris.

message = client.messages.create(
    model="zai-org/GLM-5.2-FP8",
    max_tokens=512,
    tools=[
        {
            "name": "get_weather",
            "description": "Get the weather for a city",
            "input_schema": {
                "type": "object",
                "properties": {"city": {"type": "string"}},
                "required": ["city"],
            },
        }
    ],
    messages=[{"role": "user", "content": "What is the weather in Paris?"}],
)
print(message.stop_reason)
print([b for b in message.content if b.type == "tool_use"])

tool_use
[ToolUseBlock(type='tool_use', id='toolu_01XXXX', name='get_weather', input={'city': 'Paris'})]

resp = client.messages.count_tokens(
    model="zai-org/GLM-5.2-FP8",
    messages=[{"role": "user", "content": "Hello, world"}],
)
print(resp.input_tokens)

15

export ANTHROPIC_BASE_URL="http://127.0.0.1:30000"
export ANTHROPIC_AUTH_TOKEN="dummy"                 # required by Claude Code; any non-empty string works
export API_TIMEOUT_MS="3000000"                     # long timeout — reasoning + 1M-context turns are slow
export CLAUDE_CODE_AUTO_COMPACT_WINDOW="1000000"     # let auto-compact use the full 1M window
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1   # drop autoupdater/telemetry/error-reporting noise
export CLAUDE_CODE_ATTRIBUTION_HEADER=0             # required for prefix-cache reuse — see below
export ANTHROPIC_DEFAULT_HAIKU_MODEL="glm-5.2[1m]"    # [1m] suffix enables Claude Code's 1M-context beta
export ANTHROPIC_DEFAULT_SONNET_MODEL="glm-5.2[1m]"  # [1m] suffix enables Claude Code's 1M-context beta
export ANTHROPIC_DEFAULT_OPUS_MODEL="glm-5.2[1m]"     # [1m] suffix enables Claude Code's 1M-context beta
claude