# OpenAI GPT-4.1 API

> GPT-4.1 is OpenAI's flagship non-reasoning model in the GPT-4.1 series, released in April 2025 alongside GPT-4.1 mini and nano, with text and image input and text output. OpenAI positions it for instruction following, tool calling and coding, with improved long-context comprehension across its 1M-token window and low latency because it skips a separate reasoning step. Pick it over the mini and nano tiers when output quality matters more than speed; OpenAI suggests GPT-5-class models for the most complex tasks.

Source: https://www.sandbase.ai/models/openai/gpt-4.1
API reference: https://www.sandbase.ai/models/openai/gpt-4.1/docs

## Facts

- Provider: OpenAI
- Type: Language model
- Model ID: `openai/gpt-4.1`
- Price: $2 per 1M input tokens, $8 per 1M output tokens
- Context window: 1M tokens, up to 32.8K output tokens
- Capabilities: chat, vision, structured output, function calling
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Responses API: `POST https://api.sandbase.ai/v1/responses`
- Chat Completions API: `POST https://api.sandbase.ai/v1/chat/completions`

```bash
curl -X POST https://api.sandbase.ai/v1/responses \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-4.1",
  "input": "Hello",
  "max_output_tokens": 2048
}'
```

## FAQ

### How do I call OpenAI GPT-4.1 through SandBase?

Create a SandBase API key, then send requests with the model ID "openai/gpt-4.1" to Responses API (/v1/responses) or Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### How much does OpenAI GPT-4.1 cost?

$2 per 1M input tokens and $8 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

### What is the context window of OpenAI GPT-4.1?

1M tokens of context, with up to 32.8K output tokens per response.

### How does OpenAI GPT-4.1 score on benchmarks?

OpenAI GPT-4.1 scores 12.7 on the Artificial Analysis Intelligence Index (v4.3), ranking #70 of 83 models on SandBase. Source: Artificial Analysis, measured as GPT-4.1.

### Which features does OpenAI GPT-4.1 support?

OpenAI GPT-4.1 supports vision (image input), function calling, structured output. See Specifications above for the full list.

### Do I need a separate OpenAI account?

No. One SandBase API key and balance gives you access to OpenAI GPT-4.1 and the other models in the catalog; you do not need to sign up with OpenAI separately.