# Gpt Mini (latest)

> Always resolves to the newest live Gpt Mini model — currently GPT-5.4 Mini (openai/gpt-5.4-mini). GPT-5.4 Mini is OpenAI's strongest mini model yet for coding, computer use, and subagents, delivering GPT-5.4-class capability in a faster, more cost-efficient package optimized for high-volume workloads. It supports a 400,000-token input context with 128,000 output tokens, accepts text and image inputs, and exposes reasoning tokens alongside streaming, function calling, and structured outputs.


**ID**: `openai/gpt-mini-latest`  
**Creator**: OpenAI  
**Category**: multimodal  
**Context**: 400K tokens  
**Family alias**: always resolves to the newest live family member — currently [`openai/gpt-5.4-mini`](https://anyrouter.dev/model/openai/gpt-5.4-mini). Specs below are openai/gpt-5.4-mini's.  
**Fallback order**: `openai/gpt-5.4-mini` → `openai/gpt-5-mini` → `openai/gpt-4.1-mini`  
**Pricing**: $0.75 / $4.50 per 1M · billed by your provider (BYOK)  
**Released**: 2026-03-17  
**Web page**: https://anyrouter.dev/model/openai/gpt-mini-latest

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

**Tokenizer**: GPT

**Capabilities**: chat, coding, reasoning, streaming, function-calling, 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": "openai/gpt-mini-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| openai-byok | $0.75/M (list) | $4.50/M (list) |
| opencode-zen-byok | $0.75/M (list) | $4.50/M (list) |
| router-byok | $0.75/M (list) | $4.50/M (list) |
| vercel-byok | $0.75/M (list) | $4.50/M (list) |
| nousresearch-byok | $0.75/M (list) | $4.50/M (list) |
| openrouter-byok | $0.75/M (list) | $4.50/M (list) |
| computrix-byok | $0.75/M (list) | $4.50/M (list) |
| infron-byok | $0.38/M (list) | $2.25/M (list) |
| llmgateway-byok | $0.75/M (list) | $4.50/M (list) |
| requesty-byok | $0.75/M (list) | $4.50/M (list) |
| phala-byok | $0.75/M (list) | $4.50/M (list) |
| aimlapi-byok | $1.59/M (list) | $9.52/M (list) |
| zenmux-byok | $0.75/M (list) | $4.50/M (list) |
| aihubmix-byok | $0.75/M (list) | $4.50/M (list) |
| orcarouter-byok | $0.75/M (list) | $4.50/M (list) |
| opengateway-byok | $0.75/M (list) | $4.50/M (list) |
| gmicloud-byok | $0.75/M (list) | $4.50/M (list) |
| nano-gpt-byok | $0.75/M (list) | $4.50/M (list) |
| edenai-byok | $0.75/M (list) | $4.50/M (list) |
| ofox-byok | $0.75/M (list) | $4.50/M (list) |
| abacus-byok | $0.75/M (list) | $4.50/M (list) |
| fluence-byok | $0.42/M (list) | $2.50/M (list) |
| poe-byok | $0.75/M (list) | $4.50/M (list) |
| jiekou-byok | $0.75/M (list) | $4.50/M (list) |
| nearai-byok | $0.75/M (list) | $4.50/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**: 0.8
- **HLE**: 0.2
- **τ²-Bench Telecom**: 0.4
- **SciCode**: 0.4

## Source

- Upstream docs: https://developers.openai.com/api/docs/models/gpt-5.4-mini