GPT-5.4 nano - ByteSpike

Vendor: OpenAI Model ID: gpt-5-4-nano Capability: 128K context · tool use · vision · streaming Pricing: per-token, nano tier (live rate) GPT-5.4-nano is the speed floor of the 5.4 wave. Same nano-tier price as GPT-5-nano with 5.4’s tighter output. Right pick for routing, classification, and head-of-pipeline triage where every millisecond compounds across many calls.

Request

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5-4-nano",
    "messages": [{"role": "user", "content": "Is this email spam? yes / no. Email: ..."}]
  }'

Body parameters

Field	Type	Required	Default	Notes
`model`	string	yes	—	`gpt-5-4-nano`
`messages`	array	yes	—	—
`max_tokens`	integer	no	model max	Max: 8192.
`tools`	array	no	—	Function calling supported.
`response_format`	object	no	—	JSON mode + structured output.
`stream`	boolean	no	false	SSE streaming.

Response

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "gpt-5-4-nano",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "yes"}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 142, "completion_tokens": 1, "total_tokens": 143}
}

Code examples

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model": "gpt-5-4-nano", "messages": [{"role": "user", "content": "Is this email spam?"}]}'

Streaming + caching

"stream": true for SSE. Automatic prompt caching.

Errors

Code	Trigger	Billed?
400 / 401 / 402 / 422 / 429	Standard	No
5xx	Upstream	No (auto-retry)

When to use

Routing / classification at the head of an agent pipeline.
For older 5-series nano, see GPT-5-nano.
For more capability, see GPT-5.4-mini.

Limits

Limit	Value
Context window	128K tokens
Max output	8192 tokens
Supports tool use	Yes
Supports vision	Yes
Supports streaming	Yes
Supports prompt caching	Automatic

GPT-5.2 GPT-5.4 mini

​Request

​Body parameters

​Response

​Code examples

​Streaming + caching

​Errors

​When to use

​Limits