Eligible new accounts get $0.10 in free API credit. Once per account; abuse limits apply. Create an account

Outrun
Sign in Get your key

Gemini API for Flash, Argon and Pro.

Outrun serves Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 4 Argon and Gemini 3.1 Pro Preview through one OpenAI-compatible API key. Gemini 3.8 Flash costs $0.32 per 1M input tokens and $1.58 per 1M output tokens. The same key also covers the Gemini image and video and audio models listed below. Outrun does not store your prompts or outputs on any Gemini ID.

Try Gemini in the Playground Get your API key All Gemini prices

$0.10free API credit for eligible new accounts.

4 model IDs on one Outrun key

Lowest-priced model

Gemini 3.8 Flash

gemini-3.8-flash

$0.32 in / $1.58 outper 1M tokens

58%below Google's list output price ($1.58 vs $3.75)

Endpoint
/v1/chat/completions
Format
OpenAI-compatible
Gemini IDs
4
Input from
$0.32
Privacy
Zero at Outrun

Which Gemini model ID should I use?

Start with gemini-3.8-flash for the lowest input price in this family. Keep the same key and base URL when you switch IDs. Each model name in the price table opens its own page with prices, capabilities and setup values.

  • Lowest cost per input tokengemini-3.8-flash$0.32 / $1.58
  • Gemini 3.7 Flashgemini-3.7-flash$0.95 / $4.73
  • Gemini 4 Argongemini-4-argon$1.20 / $6.00
  • Gemini 3.1 Pro Previewgemini-3.1-pro-preview$1.26 / $7.56

How much does the Gemini API cost on Outrun?

4 Gemini text models are available on Outrun, starting at $0.32 per 1M input tokens. Every ID is billed per token from prepaid USD credit; the table lists every context and cache tier.

Gemini models on OutrunUSD per 1M tokens
ModelInputOutputCached input
Gemini 3.8 Flashgemini-3.8-flash$0.32$1.58$0.04
Gemini 3.7 Flashgemini-3.7-flash$0.95$4.73$0.10
Gemini 4 Argongemini-4-argon$1.20$6.00$0.12
Gemini 3.1 Pro Previewgemini-3.1-pro-previewup to 200k tokens$1.26$7.56$0.13
Gemini 3.1 Pro Preview, over 200k tokens$2.52$11.34$0.26

Billed rates, rounded up to the cent, updated . Cached input is part of input, not an extra charge. The pricing page lists every model.

How do the prices compare?

Standard-tier output rates against the official list prices the pricing page cites.

Outrun rate and official list priceUSD per 1M tokens, input / output
ModelOutrunList priceDifferenceSource
Gemini 3.8 Flashgemini-3.8-flash$0.32/$1.58$0.75/$3.7558% lowerGoogle

What else can I use with the same key?

Image, video and audio models have their own billing units and endpoints. Open a model page for its request format.

Gemini media models on OutrunUSD per listed unit
ModelKindRate
Nano Banana / Gemini 3.1 Flash Imagegemini-3.1-flash-imageImage$0.03 per image
Nano Banana Pro / Gemini 3 Pro Imagegemini-3-pro-imageImage$0.04 per image
Veo 3.1 Fastveo-3.1-fastVideo$0.03 per second
Gemini Omni Flashgemini-omni-flashVideo$0.06 per second
Veo 3.1veo-3.1Video$0.08 per second
Gemini 3.1 TTSgemini-3.1-ttsAudio$0.04 per request
Gemini 3.8 Flash TTSgemini-3.8-flash-ttsAudio$0.32 in / $5.67 out per 1M tokens
Gemini 3 STTgemini-3-sttAudio$0.32 in / $1.89 out per 1M tokens

How do I call the Gemini API through Outrun?

Gemini text models on Outrun use the OpenAI Chat Completions format, so the OpenAI SDKs and any OpenAI-compatible app work with your Outrun key and base URL.

  1. 01

    Get your key

    Open the Telegram bot and copy your personal key. It works for Gemini and every other Outrun model.

  2. 02

    Set the base URL

    Use https://api.outrun.to/v1 exactly as shown, without /chat/completions.

  3. 03

    Send a Gemini model ID

    Put the full ID, such as gemini-3.8-flash, in the model field.

POST/v1/chat/completions 
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
Swap the model
Gemini 3.8 Flash$0.32 in/$1.58 outper 1M tokens All Gemini prices

Keep your key in an environment variable, never in client-side code.

Setup guides

Does Outrun keep my Gemini prompts?

No. Outrun does not store your prompts, images or outputs on any model, Gemini included. For each request Outrun keeps only a usage record for billing: model, tokens and cost. API calls are never added to chat history.

How Outrun handles your prompts

Gemini API questions

The model pages list every Gemini ID with its current rate and setup values.

Do I need a Google account?

No. One Outrun key and one prepaid USD balance cover Gemini and every other model on Outrun. You get the key from the Telegram bot, and eligible new accounts start with $0.10 in free credit.

Which Gemini model has the lowest input price?

Gemini 3.8 Flash starts at $0.32 per 1M input tokens and $1.58 per 1M output tokens.

How do I switch models?

Keep your Outrun key and the API base URL, and change the model ID in your request. Each model page lists its prices and setup values.

Can I try Gemini for free?

Eligible new accounts start with $0.10 in free API credit. Usage is billed at the rates on this page, and the Playground lets you try any model in your browser.

Keep exploring