Images, speech & embeddings
GPT Image 2.5, Gemini image models, text-to-speech, transcription and embeddings.
One key covers every modality beyond chat: generate and edit images with GPT Image 2.5 and Gemini image models, turn text into natural speech, transcribe audio to text, and build search and RAG pipelines with Gemini Embedding 2. All of it is metered into the same wallet with the same per-request logs.
What you get
- Image generation and editing in one endpoint
- Text-to-speech with natural voices
- Fast, accurate speech transcription
- Embeddings for search, RAG and clustering
- Consistent pricing and logs across endpoints
Common use cases
How it works
- 1Create your accountSign up for TokenRex — no card required, no waitlist.
- 2Top up your walletAdd funds through Razorpay. The confirmed amount is credited to your balance.
- 3Create an API keyGenerate a scoped key from the dashboard. Keys are shown once and stored hashed.
- 4Make your first callPoint your SDK at the TokenRex base URL. Every request is metered against your wallet in real time.
Code examples
from openai import OpenAI
client = OpenAI(api_key="sk-tb-YOUR_KEY", base_url="https://tokenrex.ai/api/public")
img = client.images.generate(
model="gpt-image-2-5",
prompt="A minimalist poster of the Howrah Bridge at dawn",
size="1024x1024",
)
print(img.data[0].url)Frequently asked questions
How are images billed?
Per image, with the rate depending on the model and quality tier — the live prices are listed below.
Which embedding model is available?
Gemini Embedding 2, billed per 1M input tokens at the market rate.
Can I edit existing images?
Yes. The images endpoint supports both generation and editing.
Related features
Create short video clips from text or images with Gemini Omni and Veo 3.1.
Lyria 3 creates music with vocals or instrumentals — clips or full tracks.
GPT-6 Astra, Claude Opus 5.5, Claude Fable 5.1, Gemini 3.8 and more — one key, one wallet.