Model capability probe

OpenAI: GPT-5.4 Pro | streaming output

Whether OpenAI: GPT-5.4 Pro supports streaming output cannot be decided from the name alone. Check model ID openai/gpt-5.4-pro, provider OpenAI, catalog params, modality, a lightweight runtime probe, and the error body together.

Model

openai/gpt-5.4-pro

OpenAI: GPT-5.4 Pro

Provider

OpenAI

62 models in catalog

Capability

streaming output

streaming-output

Catalog signal

runtime probe required

Context: 1,050,000

Capability probe summary

Model

openai/gpt-5.4-pro

Capability

streaming-output

Catalog signal

runtime probe required

Read-only check. Detection data burns after 5 minutes.

How to judge this capability

Whether OpenAI: GPT-5.4 Pro supports streaming output cannot be decided from the name alone. Check model ID openai/gpt-5.4-pro, provider OpenAI, catalog params, modality, a lightweight runtime probe, and the error body together.

Model: openai/gpt-5.4-pro
Provider: OpenAI
Capability: streaming output

How to prove it during checking

Read-only check. Detection data burns after 5 minutes.

Start with the catalog signal: runtime probe required, then verify with a real key in read-only mode.
The capability probe must bind model ID openai/gpt-5.4-pro; do not test another model from the same provider.
streaming output · supports include_reasoning · supports max_completion_tokens · supports max_tokens · supports reasoning

Next action

OpenAI: GPT-5.4 Pro streaming output should turn into an operator action: confirm sale tags, fill the capability matrix, change route, suggest a fallback model, or mark unsupported for now.

Read-only check. Detection data burns after 5 minutes.
Catalog signal: runtime probe required
Context: 1,050,000

Open key checker

Read-only check. Detection data burns after 5 minutes.