GPT 4
API model name: gpt-4
GPT 4 is OpenAI's chat model, served on the Api.Airforce unified API. It has a 8K-token context window. Capabilities include Tool calling. It is priced at $9.93 per million input tokens and $19.86 per million output tokens. That is below the provider's $30.00 official input rate. Knowledge cutoff: 2021-09-30. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.
Pricing
Api.Airforce price vs. the provider's official rate.-67%
Specifications
- Provider
- OpenAI
- Type
- chat model
- Context window
- 8K tokens
- Max output
- 4K tokens
- Knowledge cutoff
- 2021-09-30
- Input
- text
- Output
- text
Capabilities
Benchmarks
Independent evaluations and measured speed from Artificial Analysis.
GPT-4
Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)
What is GPT 4 used for?
- Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
- Agents & automation — function calling and tool use for multi-step workflows.
- Real-time experiences — stream tokens for responsive chat and apps.
GPT 4 vs. similar models
| Model | Intelligence | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| GPT 4 | 6.8 | 8K | $9.93 | $19.86 |
| Babbage 002 | — | — | $0.34 | $0.34 |
| Chatgpt 4o Latest | — | — | $2.75 | $14.50 |
| Codex Auto Review | — | — | $0.33 | $1.99 |
Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.
Related models
GPT 4 — frequently asked questions
- How much does GPT 4 cost?
- GPT 4 is billed pay-as-you-go at $9.93 per 1M input tokens and $19.86 per 1M output tokens. There is no subscription — you only pay for what you use.
- What is the context window of GPT 4?
- GPT 4 supports a context window of up to 8K tokens. It can return up to 4K tokens in a single response.
- What can GPT 4 do?
- GPT 4 supports Tool calling.
- Is GPT 4 free to use?
- GPT 4 is a paid, pay-as-you-go model — no subscription, you are only charged for usage.
- How do I use GPT 4 via the API?
- GPT 4 is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID gpt-4 with your Api.Airforce API key.
- Who makes GPT 4?
- GPT 4 is OpenAI's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.
Use GPT 4 via the API
OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass gpt-4 as the model.
curl https://api.airforce/v1/chat/completions \
-H "Authorization: Bearer $AIRFORCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4",
"messages": [{ "role": "user", "content": "Hello!" }]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
model: "gpt-4",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);