OpenAI
OpenAI serves 36 models on LLM API: 27 text models, 1 image model, 5 audio models and 3 embedding models, all from OpenAI.
Models and prices
Prices when OpenAI serves the request.
No OpenAI model matches your search.
Text 27
Prices per 1M tokens
 GPT-6 Astraopenai/gpt-6-astra | $10 | $50 | $1 | 1.05M |
|---|---|---|---|---|
GPT-6.1 Solopenai/gpt-6.1-sol | $2 | $10 | $0.1 | 1.05M |
GPT-6.1 Terraopenai/gpt-6.1-terra | $1 | $5 | $0.05 | 1.05M |
GPT-6 Lunaopenai/gpt-6-luna | $0.1 | $0.5 | $0.01 | 1.05M |
GPT-6 Solopenai/gpt-6-sol | $2 | $10 | $0.1 | 1.05M |
GPT-5.6 Lunaopenai/gpt-5.6-luna | $0.2 | $1.2 | $0.02 | 1.05M |
GPT-5.6 Solopenai/gpt-5.6-sol | $4 | $20 | $0.4 | 1.05M |
GPT-5.6 Terraopenai/gpt-5.6-terra | $2 | $12 | $0.2 | 1.05M |
GPT-5.5openai/gpt-5.5 | $5 | $30 | $0.5 | 1.05M |
GPT-5.4 Miniopenai/gpt-5.4-mini | $0.75 | $4.5 | $0.07 | 400K |
GPT-5.4openai/gpt-5.4 | $2.5 | $15 | $0.25 | 1.05M |
GPT-5.4 Proopenai/gpt-5.4-pro | $30 | $180 | $3 | 1.05M |
GPT-5.2openai/gpt-5.2 | $1.75 | $14 | $0.175 | 400K |
GPT-5.2 Proopenai/gpt-5.2-pro | $21 | $168 | — | 400K |
GPT-4.1 Miniopenai/gpt-4.1-mini | $0.4 | $1.6 | $0.1 | 1M |
GPT-4.1openai/gpt-4.1 | $2 | $8 | $0.5 | 1M |
GPT-4o Miniopenai/gpt-4o-mini | $0.15 | $0.6 | $0.075 | 128K |
GPT-6 Luna Decisionsopenai/gpt-6-luna-decisions | $0.1 | — | $0.01 | 1.05M |
GPT-5.4 NanoDeprecatedopenai/gpt-5.4-nano | $0.2 | $1.25 | $0.02 | 400K |
GPT-5.3 CodexDeprecatedopenai/gpt-5.3-codex | $1.75 | $14 | $0.175 | 400K |
GPT-5.1Deprecatedopenai/gpt-5.1 | $1.25 | $10 | $0.125 | 400K |
GPT-5 NanoDeprecatedopenai/gpt-5-nano | $0.05 | $0.4 | $0.005 | 400K |
GPT-5 MiniDeprecatedopenai/gpt-5-mini | $0.25 | $2 | $0.025 | 400K |
GPT-5Deprecatedopenai/gpt-5 | $1.25 | $10 | $0.125 | 400K |
GPT-5 ProDeprecatedopenai/gpt-5-pro | $15 | $120 | — | 400K |
o3Deprecatedopenai/o3 | $2 | $8 | — | 200K |
GPT-4oDeprecatedopenai/gpt-4o | $2.5 | $10 | $1.25 | 128K |
Image 1
Price per image
GPT Image 2openai/gpt-image-2 | $0.22/ image | Generate, Edit |
|---|
Audio 5
Price per minute of audio or per 1K characters
GPT Live 1gpt-live-1 | Realtime voice | $0.05/ minute |
|---|---|---|
GPT-4o Mini TTSgpt-4o-mini-tts | Text to speech | $0.0006/ 1K characters |
GPT-4o Mini Transcribegpt-4o-mini-transcribe | Transcription | $0.003/ minute |
GPT-4o Transcribegpt-4o-transcribe | Transcription | $0.006/ minute |
OpenAI Whisperwhisper-1 | Transcription | $0.006/ minute |
Embeddings 3
Price per 1M input tokens
Text Embedding 3 Smalltext-embedding-3-small | $0.02 | 1536 | 8K |
|---|---|---|---|
Text Embedding 3 Largetext-embedding-3-large | $0.13 | 3072 | 8K |
Text Embedding Ada 002text-embedding-ada-002 | $0.1 | 1536 | 8K |
Send requests to OpenAI
Put openai/ before a model ID and the request goes to OpenAI. If OpenAI’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends X-No-Fallback: true. Routing docs
Example: GPT-6 Astra
POST /v1/chat/completionsSet LLMAPI_KEY to your LLM API key.Chat Completions docs
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.llmapi.ai/v1",
api_key=os.environ["LLMAPI_KEY"],
)
response = client.chat.completions.create(
model="openai/gpt-6-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.llmapi.ai/v1",
apiKey: process.env.LLMAPI_KEY,
});
const response = await client.chat.completions.create({
model: "openai/gpt-6-astra",
messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6-astra",
"messages": [{"role": "user", "content": "Hello"}]
}'Prices synced November 13, 2026.