Pular para o conteúdo principal

OpenAIAdded Mar 27, 2026Anonymized

GPT-5.4 Mini

GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.

openai-gpt-54-miniPOST https://api.venice.ai/api/v1/responses
Input / output
$0.75 / $4.50
per 1M tokens
Context
400K
128K max output
Reasoning
none, low, medium, high, xhigh
default high
Cached input
$0.075
90% off input
Modalities
Text, image
out: text

Pricing

USD per 1M tokens
Input
$0.75
Cached input
$0.075
Output incl. reasoning
$4.50
Similar modelsInputOutputOutput price, relative
GPT-5.4 Mini$0.75$4.50
Qwen 3.5 397B$0.75$4.50
Grok 4.20$1.42$2.83
Grok 4.20 Multi-Agent$1.42$2.83
Grok 4.3$1.42$2.83

Prompt caching is automatic; see Prompt caching.

Specs

Model ID
openai-gpt-54-mini
Endpoint
POST /api/v1/responses
Context window
400,000 tokens
Max output
128,000 tokens
Reasoning effort
reasoning_effort: none | low | medium | high | xhigh · default high · guide
Served precision
Set by the upstream provider
Added
Mar 27, 2026

Capabilities

Modalities
Text
Input and output
Image
Input only · up to 10
Audio
Not supported
Video
Not supported
Features
Streaming (SSE)
Supported
Function calling
Supported
Structured output (json_schema)
Supported
Reasoning effort
none, low, medium, high, xhigh
Prompt caching
Supported
Web search
venice_parameters
X search
Not supported
Log probabilities
Not supported
Fine-tuning
Not supported
Image generation
Not supported
POST/api/v1/responsesRecommended

OpenAI reasoning models are designed around the Responses API: reasoning, tool calls and messages come back as typed output items. /chat/completions stays fully supported.

curl https://api.venice.ai/api/v1/responses \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai-gpt-54-mini",
"input": "Explain TEE attestation in two sentences.",
"reasoning": { "effort": "high" }
}'

Privacy

Tier 1 · this model
Anonymized

Venice hides your identity and stores no prompts. OpenAI still sees the content.

Tier 2
Private

Not available

Tier 3
TEE

Not available

Tier 4
End-to-end encrypted

Not available