OpenAIAI provider

OpenAI models, now on TokenRex

TokenRex gives you OpenAI's flagship GPT models — plus image, voice, transcription and embedding models — through one OpenAI-compatible API key. Keep the official OpenAI SDK, change the base URL, and pay only for the tokens you use from a prepaid wallet.

Models available
90
Model families
29
Types
6
Claim free credits See all OpenAI models
Sam Altman of OpenAI speaking on stage at TechCrunch Disrupt San Francisco 2019
Sam Altman of OpenAI at TechCrunch Disrupt San Francisco, 2019. Photo: TechCrunch, CC BY 2.0, via Wikimedia Commons.

OpenAI flagship models

The OpenAI models most people start with. Prices are live and update automatically.

OpenAIChat & reasoning

GPT-6 Astra

Advanced intelligence for complex reasoning, coding, research, and document creation.

$10.00 in · $50.00 out / 1M

gpt-6-astra
View model details
OpenAIChat & reasoning

GPT-6.1 Sol

Advanced coding and reasoning for complex professional workflows.

$2.00 in · $10.00 out / 1M

gpt-6.1-sol
View model details
OpenAIChat & reasoning

GPT-6 Sol

Balanced reasoning and capability for general-purpose professional work.

$2.00 in · $10.00 out / 1M

gpt-6-sol
View model details
OpenAIChat & reasoning

GPT-6 Luna

Cost-efficient intelligence for everyday tasks and high-volume applications.

$0.10 in · $0.50 out / 1M

gpt-6-luna
View model details
OpenAIChat & reasoning

GPT-5.6 Sol

Advanced intelligence for complex reasoning, coding, and agent workflows.

$4.00 in · $20.00 out / 1M

gpt-5.6-sol
View model details
OpenAIImage generation

GPT Image 2.5 Sunburst

High-quality image generation and editing for visually demanding creative work.

$5.00 in · $30.00 out / 1M

gpt-image-2.5-sunburst
View model details
OpenAILive voice

GPT Live 1

Real-time voice conversations with low latency and support for interruptions.

$0.00083 per second

gpt-live-1
View model details
OpenAISpeech-to-text

GPT Transcribe

Convert speech into text with language and vocabulary guidance.

$0.00458 per audio minute

gpt-transcribe
View model details

What you can do with OpenAI on TokenRex

Chat and reasoning

GPT-6 and GPT-5.x models for writing, analysis, research and agents. Many families offer Fast, Deep and Max thinking versions.

Coding and agents

Use GPT models in Cursor, Codex CLI, VS Code, OpenCode and your own agents with function calling you define.

Image generation and editing

GPT Image 2.5 Sunburst for top quality, Flare for speed, and GPT Image 2 for general work.

Voice, speech and live calls

Text-to-speech, transcription with GPT Transcribe, and real-time voice conversations with GPT Live 1.

Embeddings

text-embedding-3 models for search, retrieval (RAG), clustering and recommendations.

Cached input pricing

When OpenAI reports cached prompt tokens, TokenRex bills them at the lower cache-read rate shown on each model page.

Popular ways people use it

  • Customer-support assistants that answer from your own documents
  • Coding agents and code review inside your editor
  • Marketing, product and social images from a text prompt
  • Voice bots and call transcription
  • Semantic search over help centres and knowledge bases
  • Data extraction from emails, invoices and PDFs

How it works

TokenRex sits between your app and OpenAI. You send a normal API request with your TokenRex key; we check the key and your balance, pass the request to OpenAI, stream the answer back, and bill the exact usage OpenAI reports.

  1. Your app

    SDK, agent or BYOK tool

  2. TokenRex

    Checks key and balance

  3. OpenAI

    Runs the OpenAI model

  4. Answer + bill

    Streamed back, billed per use

  1. 1

    Create a free account

    Sign up with email or Google. New accounts can claim free starter credit.

  2. 2

    Create an API key

    Open API keys in your dashboard and create a key. Keep it private.

  3. 3

    Point your app at TokenRex

    Set the base URL to https://tokenrex.ai/api/public in your SDK or BYOK app and paste your key.

  4. 4

    Choose a model ID

    Copy the exact model ID from the list on this page, for example from a flagship card.

  5. 5

    Pay only for what you use

    Each request is billed at the live model price and deducted from your prepaid wallet.

Python · OpenAI SDK

Configuration
from openai import OpenAI

client = OpenAI(
    base_url="https://tokenrex.ai/api/public",
    api_key="YOUR_TOKENREX_KEY",
)

reply = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "Summarise this week's sales notes in five bullets."}],
)
print(reply.choices[0].message.content)

Endpoints for OpenAI models

  • POST /v1/chat/completionsChat and reasoning, with streaming
  • POST /v1/images/generationsCreate images
  • POST /v1/images/editsEdit images
  • POST /v1/audio/speechText-to-speech
  • POST /v1/audio/transcriptionsSpeech-to-text
  • POST /v1/embeddingsEmbeddings
  • WSS /v1/liveLive voice calls with GPT Live 1

All OpenAI models on TokenRex

90 models in 29 families. Open a model to see every version, cache rates and limits.

Compare models

Chat & reasoning

Price

Image generation

Price

Text-to-speech

Price

Speech-to-text

Price

Embeddings

Price

Live voice

Price

Pricing and billing

Prepaid wallet

Top up once and every request is deducted from your balance. No subscription and no monthly minimum.

Cache-aware billing

If OpenAI reports cached input tokens, they are billed at the model's lower cache-read rate.

Fast versions

Where offered, Fast versions answer about 2x faster at 2x the price.

OpenAI on TokenRex — common questions

Can I use the official OpenAI SDK?

Yes. Set the SDK's base URL to the TokenRex address and use your TokenRex API key. Your existing code keeps working.

Do OpenAI model IDs change?

TokenRex uses short model IDs such as gpt-6-astra or gpt-image-2.5-sunburst. Copy the exact ID from the model list on this page.

How am I charged?

Per token (or per image, minute or second for media models) at the live price shown on each model page, deducted from your prepaid wallet.

What are Fast versions?

Fast versions use priority routing for roughly 2x faster responses at 2x the price.

Can I use a TokenRex key in the ChatGPT app?

No. The ChatGPT app does not accept custom API keys. Use the key in your own apps, the OpenAI SDK, or BYOK tools listed in Integrations.

Other AI providers on TokenRex

AnthropicAnthropic modelsGoogleGoogle modelsTypesafeTypeSafe AI models

OpenAI and its logo are trademarks of their owner and are shown only to identify the models available. TokenRex is an independent service by Asirex Labs and is not affiliated with or endorsed by OpenAI.