sgl-project/sglang · error · ValueError

Model is required

Error message

Model is required

What it means

Raised by the pydantic field validator on the MessagesRequest model when the model field is empty or missing after parsing. The Anthropic-compatible endpoint requires a model identifier to route the request, so an empty string or null model is rejected with a 400.

Source

Thrown at python/sglang/srt/entrypoints/anthropic/protocol.py:386

    stop_sequences: Optional[list[str]] = None
    stream: Optional[bool] = False
    system: Optional[Union[str, list[AnthropicContentBlock]]] = None
    temperature: Optional[float] = None
    thinking: Optional[AnthropicThinkingParam] = None
    tool_choice: Optional[AnthropicToolChoice] = None
    tools: Optional[list[AnthropicTool]] = None
    top_k: Optional[int] = None
    top_p: Optional[float] = None
    # Claude 4.7 fields. The Anthropic SDK / Claude Code attach these even
    # when targeting non-Anthropic backends, so the schema must accept them.
    output_config: Optional[AnthropicOutputConfig] = None
    betas: Optional[list[str]] = None

    @field_validator("model")
    @classmethod
    def _validate_model(cls, v):
        if not v:
            raise ValueError("Model is required")
        return v

    @field_validator("max_tokens")
    @classmethod
    def _validate_max_tokens(cls, v):
        if v <= 0:
            raise ValueError("max_tokens must be positive")
        return v


# ---------- Stream deltas ----------
# Content-block deltas (discriminated by ``type``) vs message-end delta
# (separate model; the wire format does not put ``type`` inside its payload).


class TextDelta(BaseModel):
    type: Literal["text_delta"] = "text_delta"
    text: str

View on GitHub (pinned to 0132848349)

Solutions

1. Set model to a deployed model name, e.g. the --model-path the server was launched with
2. Check the client's model configuration/env vars resolve to a non-empty string
3. Verify the request body actually includes the model field

Example fix

// before
{"model": "", "messages": [...]}
// after
{"model": "my-model", "messages": [...]}

if not model or not model.strip():
    raise ValueError("model must be a non-empty string")

def is_valid_model(m: object) -> bool:
    return isinstance(m, str) and len(m.strip()) > 0

When it happens

Trigger: POST /v1/messages with model: "" or omitting the model field (if the client schema allows), or a client that substitutes an empty model env var.

Common situations: Model name read from an unset environment variable or config key; templating that renders an empty model placeholder; proxy stripping the model field before forwarding.

Understand the failure class

Background: "Missing required field" and "field is required" errors: why libraries reject payloads that omit mandatory fields — this error's family across 20 libraries.

Related errors

• thinking.budget_tokens must be >= 1024 (got {})
• thinking.budget_tokens is not allowed when thinking.type is
• thinking.display is not allowed when thinking.type is 'disab
• thinking.budget_tokens is not allowed when thinking.type is
• max_tokens must be positive

AI-assisted analysis of sgl-project/sglang@0132848349 (2026-08-28). Data as JSON: /api/errors/db1b4c5a9d44e089. Report an issue: GitHub.