Provider pricing hub

Gemini API pricing, every model on one page.

Gemini API prices on RouterPlex run from $0.10 (Gemini 2.5 Flash Lite) to $2.00 per 1M input tokens, Google's list price with 0% markup. Four models are on intro rates ending November or December 2026. Top-ups have a $0 fee, by card from $5 or crypto; balances stop at $0 and each key has a hard USD cap.

Prices checked 20 October 2026 from the live catalog. Google's pricing page last checked 20 Oct 2026: ai.google.dev/gemini-api/docs/pricing

Gemini on this key20 October 2026

Routes

$0.10

Cheapest input / 1M

Markup 0%

Gemini family

Published catalog rates.

Agent-turn cost uses 100K input and 10K output. Intro badges and notes come from each catalog row.

Model route	Context	Input / 1M	Cached input / 1M	Output / 1M	Agent turn
Gemini 2.5 Flash Lite gemini-2.5-flash-lite	1M	$0.10	not offered	$0.40	$0.014
Gemini 3.1 Flash Lite gemini-3.1-flash-lite	1M	$0.25	not offered	$1.50	$0.040
Gemini 2.5 Flash gemini-2.5-flash	1M	$0.30	not offered	$2.50	$0.055
Gemini 3 Flash gemini-3-flash	1M	$0.50	not offered	$3.00	$0.080
Gemini 3.6 Flash gemini-3.6-flashIntro to 31 December 2026	1M	$0.75	not offered	$3.75	$0.11
Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.
Gemini 3.7 Flash gemini-3.7-flashIntro to 31 December 2026	1M	$0.75	not offered	$3.75	$0.11
Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.
Gemini 3.8 Flash gemini-3.8-flashIntro to 31 December 2026	1M	$0.75	not offered	$3.75	$0.11
Google introductory pricing through December 31, 2026; the published rate becomes $1.50 input / $7.50 output per 1M tokens on January 1, 2027.
Gemini 3.5 Flash gemini-3.5-flash	1M	$1.50	not offered	$9.00	$0.24
Gemini 4 Argon gemini-4-argonIntro to 30 November 2026	1M	$2.00	not offered	$10.00	$0.30
Google introductory pricing through November 30, 2026; the published rate becomes $4 input / $20 output per 1M tokens on December 1, 2026. Thinking tokens are billed as output. Set reasoning_effort to low, medium (default) or high. Output is capped at 64K tokens per response.
Gemini 3.1 Pro gemini-3.1-pro	1M	$2.00	not offered	$12.00	$0.32

No Gemini route in this catalog lists a cached-input rate, so that column reads "not offered".

Gemini pricing calculator

Same workload. Every Gemini route.

Defaults are a 10K-in / 1K-out request, 3,000 times a month. Switch to the 100K / 10K agent turn if you are costing a coding loop.

Workload calculator

Catalog rates · USD · no markup

10K in + 1K out × 3,000 req$100 of tokens

Route	Per request	Monthly	$100 buys
Gemini 2.5 Flash Lite Google	$0.0014	$4.20	71,428 req
Gemini 3.1 Flash Lite Google	$0.0040	$12.00	25,000 req
Gemini 2.5 Flash Google	$0.0055	$16.50	18,181 req
Gemini 3 Flash Google	$0.0080	$24.00	12,500 req

Estimates apply live catalog input and output rates only. Actual spend follows the tokens your client sends and the model returns. Image-generation routes are omitted because they are not a chat turn.

Intro rates

What changes when Gemini intro prices end.

Dates and later rates come from each route's catalog note. The bill follows the catalog row on the day you send the request.

Model route	Rate now / 1M	Intro ends	Published rate after
Gemini 3.6 Flash	$0.75 / $3.75	31 December 2026	$1.50 / $7.50 from 1 January 2027
Gemini 3.7 Flash	$0.75 / $3.75	31 December 2026	$1.50 / $7.50 from 1 January 2027
Gemini 3.8 Flash	$0.75 / $3.75	31 December 2026	$1.50 / $7.50 from 1 January 2027
Gemini 4 Argon	$2.00 / $10.00	30 November 2026	$4.00 / $20.00 from 1 December 2026

Call it

Use Gemini from Claude Code or the OpenAI SDK.

Claude Code and the Anthropic SDK use https://api.routerplex.com. The OpenAI SDK, Cursor and Cline use https://api.routerplex.com/v1. Same key, same catalog id, same per-key budget. Swap gemini-3-flash for any id in the table.

Claude Code (shell)

export ANTHROPIC_BASE_URL=https://api.routerplex.com
export ANTHROPIC_AUTH_TOKEN="$ROUTERPLEX_API_KEY"
export ANTHROPIC_MODEL=gemini-3-flash
claude

OpenAI SDK (Python)

import os
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.routerplex.com/v1",
    api_key=os.environ["ROUTERPLEX_API_KEY"],
)
reply = client.chat.completions.create(
    model="gemini-3-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)

How to pick

Which Gemini model to pick.

These notes only use catalog fields: price, context, and mode. They are not quality rankings.

Cheapest per agent turn

Gemini 2.5 Flash Lite costs about $0.014 for a 100K-in / 10K-out turn at $0.10 / $0.40 per 1M. Use it for short, retryable tasks.

Intro-rate risk

Gemini 4 Argon keeps the intro rate only through 30 November 2026; after that the published rate is $4.00 / $20.00. Budget a long-running job on the later rate.

One key, two SDK shapes

Claude Code and the Anthropic SDK use https://api.routerplex.com. Cursor, Cline, and the OpenAI SDK use https://api.routerplex.com/v1. Same key, same catalog IDs, same per-key budget.

Setup notes for Gemini 4 Argon, Gemini 3.8 Flash and Gemini 3.8 Live, plus the OpenAI-compatible API guide. Compare the rest of the catalog on all model pricing, the OpenAI, Anthropic, DeepSeek and Kimi hubs, the cheapest-first ledger, or RouterPlex vs OpenRouter. The plain model list lives in the docs.

Before you bill production

Gemini pricing, in questions.

01How much does the Gemini API cost?+

As of 20 October 2026, RouterPlex bills Gemini at Google's list price with 0% markup: $0.10 to $2.00 per 1M input tokens and $0.40 to $12.00 per 1M output tokens. Gemini 2.5 Flash Lite is the low end and Gemini 4 Argon and Gemini 3.1 Pro the high end. Top-ups have a $0 fee and the balance stops at $0.

02Which Gemini model is cheapest?+

Gemini 2.5 Flash Lite at $0.10 / $0.40 per 1M tokens, about $0.014 for a 100K-in / 10K-out agent turn. Cheapest here means catalog price per turn, not quality. The full ranking across every provider is on the cheapest-first ledger at /models/cheapest.

03When do the Gemini Flash intro prices end?+

Gemini 3.6 Flash, Gemini 3.7 Flash and Gemini 3.8 Flash are at $0.75 / $3.75 per 1M through 31 December 2026, then Google's published rate becomes $1.50 / $7.50 from 1 January 2027. RouterPlex bills whichever rate the catalog row shows on the day of the request.

04What will Gemini 4 Argon cost after November?+

Gemini 4 Argon is $2.00 / $10.00 per 1M tokens through 30 November 2026. Google's published rate becomes $4.00 / $20.00 from 1 December 2026, and the catalog row moves with it. Thinking tokens bill as output.

05Does RouterPlex offer Gemini cached-input pricing?+

Not today. No Gemini route in this catalog lists a cached-input rate, so the table shows "not offered". Google publishes its own context-caching prices on ai.google.dev; those are Google's rates for Google accounts, not a RouterPlex rate.

06Can I use Gemini with Claude Code or Cursor?+

Yes. Claude Code and the Anthropic SDK use https://api.routerplex.com with your RouterPlex key as ANTHROPIC_AUTH_TOKEN. Cursor, Cline and the OpenAI SDK use https://api.routerplex.com/v1. Set the model to a catalog id such as "gemini-3-flash". You do not need a Google Cloud project or an AI Studio key.

07Why might a number differ from ai.google.dev?+

This page shows what RouterPlex bills, read from the live catalog on 20 October 2026. Google lists free-tier quotas, batch rates, grounding and audio prices that are not RouterPlex routes, and its intro rates change on fixed dates. If the two disagree, the catalog row is what a request on your RouterPlex key costs.

Route Gemini from one balance

Try Gemini with $1, no card.

Try it with $1 of test credit, no card. Guided setup shows the exact Claude Code config for Gemini 3 Flash.

Eligible verified accounts get the $1 once. It never expires.

All routes Try it with $1, no card