treg.to / Catalog / Google AI (Gemini API)
3 tools · from $0.04/success · $0.000 markup

Google AI (Gemini API): 3 tools from $0.04/success

Generate and edit images with Gemini 3 Pro Image on Google's own API. 3 tools for your agent through one treg.to key, priced at the provider's own rate from $0.04/success, with no Google AI (Gemini API) signup.
Start freeSee all 3 toolsAPI docs ↗
$1.00 of free credit once per new verified account · no card · platform tools need no provider signup
3 of 3 tools on this page are live-verified against the provider.
works in
ChatGPTClaudeClaude CodeCodexCursorGrokGemini CLI
What your agent can now do

Google AI (Gemini API), one prompt away

AGENT
ChatGPTClaudeClaude CodeCodexCursorGrokGemini CLI
gemini 3 Pro Image✓
gemini 3.1 Flash Image (Nano Banana 2)✓
gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)✓
→
▚ treg
$ treg call google-ai.image-gen.gemini-3-pro-image
✓ 200 · $0.15-$0.26/success
$ treg call google-ai.image-gen.gemini-3-1-flash-image
✓ 200 · $0.05-$0.165/success
$ treg call google-ai.image-gen.gemini-3-1-flash-lite-image
✓ 200 · $0.04/success
$ _
→
Google AI (Gemini API)NO SIGNUP
Generate and edit images with Gemini 3 Pro Image on Google's own API.
⚒ 3 TOOLS · metered per call

AI generation · https://generativelanguage.googleapis.com/v1beta

Set up

Set up Google AI (Gemini API) in Claude Code, Codex or any agent

1Give this to your agent
in your agent's chat
set up treg — https://treg.to/llms.txt
2Or add the MCP server yourself
claude code
claude mcp add --transport http treg https://treg.to/mcp

ChatGPT

Settings → Connectors → add https://treg.to/mcp as a custom connector.

Grok bot

Add https://treg.to/mcp as a remote MCP connector in its tool settings.

Claude Desktop

Settings → Connectors → Add custom connector → https://treg.to/mcp.

Cursor, Codex, any MCP client

Point it at https://treg.to/mcp (HTTP transport).

CLI

curl -fsSL https://treg.to/install.sh | sh

Plain HTTP

LangChain, CrewAI or any code: /call/<tool-id> + X-Treg-Token: <token>. No SDK.

Try it

What's the best way to ask?

the prompt
Using treg, gemini 3 Pro Image. Show me the price first.

Run one directly

a live-verified call
treg call google-ai.image-gen.gemini-3-pro-image --method POST --query model=gemini-3-pro-image --query 'fields=candidates(content(parts(text,inlineData)),finishReason),usageMetadata,modelVersion,responseId,promptFeedback' --data '{"contents":[{"parts":[{"text":"A clean editorial illustration of a paper airplane."}]}],"generationConfig":{"responseModalities":["IMAGE"],"imageConfig":{"imageSize":"1K","aspectRatio":"1:1"}}}'
Why treg.to

Why call Google AI (Gemini API) through treg.to

No Google AI (Gemini API) signup

Eligible tools run on treg.to's key, metered per call from a prepaid balance.

Price before the call

The provider's own rate, $0.000 markup. How billing works.

No subscription, no seats

Platform calls are charged per call. $1.00 free per new team, no card to start.

Your own Google AI (Gemini API) key is free

Register it and those calls are never metered. Your key always wins.

Switch by changing a word

Another provider is a different word in the prompt, not a new integration.

One key, the whole catalog

The same token calls PiAPI, reAPI, Replicate and 3,338 other tools.

The shelf

All 3 Google AI (Gemini API) tools

Image generation · 3 tools
  • Google: Gemini 3.1 Flash Image (Nano Banana 2) · Platform + BYOK · live-verified · $0.05-$0.165/success
    Generate or edit one image with Gemini 3.1 Flash Image at 512px, 1K, 2K or 4K on Google's own API, from a prompt and optional reference images; the image returns inline as base64. google-ai.image-gen.gemini-3-1-flash-image
    Token-metered at Google's paid-tier rates: input $0.50/M, text and thinking output $3/M, image output $60/M (the image term adds $57/M on top of candidatesTokenCount, which already counts it at $3/M). Live 2026-09-30 the image meter read 747 tokens at 512px, 1,120 at 1K, 1,680 at 2K and 2,520 at 4K ($0.045 / $0.067 / $0.101 / $0.151 per image), plus about 400 text tokens in candidatesTokenCount; no thoughtsTokenCount is reported. A 4K answer is about 23 MB and is spooled. The row is the hold; usageMetadata settles.
  • Google: Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) · Platform + BYOK · live-verified · $0.04/success
    Generate or edit one 1K image with Gemini 3.1 Flash Lite Image on Google's own API, the cheapest Gemini image model; the image returns inline as base64. google-ai.image-gen.gemini-3-1-flash-lite-image
    Token-metered at Google's paid-tier rates: input $0.25/M, text and thinking output $1.50/M, image output $30/M (the image term adds $28.50/M on top of candidatesTokenCount). Only 1K exists: live 2026-09-30, 512, 2K and 4K each answered 400 'not supported for this model'. A 1K image reads 1,120 image tokens ($0.0336) plus about 400 text tokens; an answer is about 2.2 MB, so it is buffered, not spooled. The row is the hold; usageMetadata settles.
  • Google: Gemini 3 Pro Image (Nano Banana Pro) · Platform + BYOK · live-verified · $0.15-$0.26/success
    Generate or edit one image with Gemini 3 Pro Image at 1K, 2K or 4K on Google's own API, from a prompt and optional reference image URLs; the image returns inline as base64. google-ai.image-gen.gemini-3-pro-image
    Token-metered at Google's paid-tier rates: input $2/M, text and thinking output $12/M, image output $120/M (the image term adds $108/M on top of candidatesTokenCount, which already counts it at $12/M). One 1K or 2K image is 1,120 image tokens ($0.1344), a 4K image 2,000 ($0.24); a reference image adds about 258 input tokens. The row is the hold; usageMetadata settles. A blocked image answers HTTP 200 with finishReason IMAGE_SAFETY, empty content and no image: live, it settled its prompt and thinking tokens only ($0.003956), not the hold. Check finishReason before reading parts.

Reliability badges come from live traffic through treg.to. Live-verified means a successful provider check; it does not verify every request variant.

Related

Same jobs, other providers

These providers answer some of the same capabilities as Google AI (Gemini API). The platform pages show them on one row with rate and coverage; choosing is yours, treg.to does not route between providers automatically.

also on the catalog
PiAPIreAPIReplicate
Questions

Before you start

Do I need a Google AI (Gemini API) account?

No. Eligible tools run on treg.to's key and the call is metered from your team's prepaid balance, priced up front. If your team registers its own Google AI (Gemini API) key, that key always wins and those calls are never metered.

What does a call cost?

Each tool on this page shows its rate; the cheapest is $0.04/success. The rate is the provider's own and treg.to adds no markup; it is billed per call from a prepaid balance. It is not Google AI (Gemini API)'s subscription pricing, which is on their own site. New teams start with $1.00 of free credit.

How do I add Google AI (Gemini API) to Claude Code?

Run: claude mcp add --transport http treg https://treg.to/mcp. One MCP server carries Google AI (Gemini API) and the rest of the catalog.

Which frameworks does it work with?

Anything that speaks MCP (Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, Grok) and anything that can make an HTTP request (LangChain, CrewAI, LlamaIndex, plain code).

Is this the official Google AI (Gemini API) MCP server?

No. treg.to serves Google AI (Gemini API)'s real API through its own metered proxy: the request is the provider's own, the credential is injected server-side, and the answer is relayed verbatim. The official Google AI (Gemini API) channels are linked above.