GoogleAI provider

Google's Gemini, Veo and Lyria models, now on TokenRex

TokenRex brings Google's full creative and reasoning line-up to one OpenAI-compatible API: Gemini chat models, Gemini image generation, Veo video, Lyria music, text-to-speech, transcription and embeddings. One key, one wallet, and the same request format you already use.

Models available
32
Model families
27
Types
7
Claim free credits See all Google models
Google headquarters building with the Google sign at the Googleplex in Mountain View, California
The Googleplex, Google's headquarters in Mountain View, California. Photo: Grendelkhan, CC BY-SA 3.0, via Wikimedia Commons.

Google flagship models

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

GoogleChat & reasoning

Gemini 4 Argon

Advanced reasoning and long-horizon coding for demanding workflows.

$2.00 in · $10.00 out / 1M

gemini-4-argon
View model details
GoogleChat & reasoning

Gemini 3.8 Flash

Fast multimodal intelligence for coding, reasoning, and agentic workflows.

$0.75 in · $3.75 out / 1M

gemini-3.8-flash
View model details
GoogleChat & reasoning

Gemini 3.1 Pro

Advanced multimodal reasoning for complex problems and coding tasks.

$2.00 in · $12.00 out / 1M

gemini-3.1-pro-preview
View model details
GoogleImage generation

Gemini 3 Pro Image

Create and edit detailed images with support for complex visual instructions.

$0.134 per image

gemini-3-pro-image
View model details
GoogleVideo generation

Veo 3.1

Generate high-quality video with cinematic control and synchronized audio.

$0.40 per second

veo-3.1
View model details
GoogleMusic generation

Lyria 3 Pro

Create longer music tracks with vocals or instrumentals from creative prompts.

$0.08 per song

lyria-3-pro-preview
View model details
GoogleText-to-speech

Gemini 3.1 Flash TTS

Generate natural-sounding speech from text with low-latency synthesis.

$0.0341 per 1k chars

gemini-3.1-flash-tts-preview
View model details
GoogleEmbeddings

Gemini Embedding 2

Create multimodal embeddings for semantic search, retrieval, and recommendations.

$0.20 in / 1M

gemini-embedding-2
View model details

What you can do with Google on TokenRex

Multimodal reasoning

Gemini 4 Argon and Gemini 3.8 Flash for chat, coding, long documents and agent workflows.

Image generation and editing

Gemini image models create and edit detailed images, including 2K and 4K versions.

Video with Veo

Generate short videos with Veo 3.1 or the lower-cost Veo 3.1 Lite. Start a job, then check its status.

Music with Lyria

Create music clips and longer tracks from a text or image prompt, returned as MP3.

Speech and transcription

Natural text-to-speech voices and multilingual transcription.

Embeddings

Gemini embeddings for semantic search, retrieval and recommendations.

Popular ways people use it

  • Product videos and social clips with Veo
  • Background music and jingles with Lyria
  • Fast, low-cost chat and extraction with Gemini Flash
  • Image ads, thumbnails and edits
  • Voice-overs and narration in many languages
  • Search and retrieval over large document sets

How it works

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

  1. Your app

    SDK, agent or BYOK tool

  2. TokenRex

    Checks key and balance

  3. Google

    Runs the Google 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="gemini-3.8-flash",
    messages=[{"role": "user", "content": "Write three product taglines for a solar lamp."}],
)
print(reply.choices[0].message.content)

Endpoints for Google models

  • POST /v1/chat/completionsGemini chat, with streaming
  • POST /v1/images/generationsGemini image generation
  • POST /v1/videosStart a Veo video job
  • GET /v1/videos/{id}Check a video job
  • POST /v1/musicLyria music generation
  • POST /v1/audio/speechText-to-speech
  • POST /v1/audio/transcriptionsSpeech-to-text
  • POST /v1/embeddingsEmbeddings

All Google models on TokenRex

32 models in 27 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

Video generation

Price

Music generation

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 Google 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.

Google on TokenRex — common questions

Do I need a Google Cloud account?

No. You only need a TokenRex account and API key. TokenRex handles the connection to Google.

Is the Gemini native API format supported?

Not yet. Call Gemini models through the OpenAI-compatible endpoints listed on this page.

How are video and music billed?

Veo video is billed per second of video and Lyria per track, at the live price on each model page.

Are older Gemini models being retired?

Some are. Model pages show a Deprecated tag and the shutdown date Google has announced, when there is one.

Other AI providers on TokenRex

OpenAIOpenAI modelsAnthropicAnthropic modelsTypesafeTypeSafe AI models

Google 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 Google.