# 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.

**ID**: `venice/openai-gpt-54-mini`  
**Creator**: OpenAI  
**Category**: text  
**Context**: 400K tokens  
**Pricing**: $0.94 / $5.63 per 1M · billed by your provider (BYOK)  
**Released**: 2026-03-27  
**Web page**: https://anyrouter.dev/model/venice/openai-gpt-54-mini

**Input modalities**: text, image  
**Output modalities**: text  

**Capabilities**: chat, reasoning, function-calling, structured-output, streaming, vision

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "venice/openai-gpt-54-mini",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| venice-byok | $0.94/M (list) | $5.63/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.6
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.2
- **SciCode**: 0.4

## Source

- Upstream docs: https://docs.venice.ai