Gemini

Pricing

• Free tier - free input and output tokens in Google AI Studio on selected models such as Gemini 3.8 Flash; not available for Gemini 4 Argon; content used to improve Google products
• Gemini 4 Argon - $2 input / $10 output per 1M tokens through November 30, 2026, then $4 / $20 from December 1, 2026
• Gemini 3.8 Flash - $0.75 input / $3.75 output per 1M tokens through December 31, 2026, then $1.50 / $7.50 from January 1, 2027
• Batch API - 50% cost reduction on paid tier
• Enterprise - via Gemini Enterprise Agent Platform, contact sales

Install

pip install -U google-genai

npm install @google/genai

Models

Gemini 4 Argon (gemini-4-argon) is the flagship for coding, agents, math and science, with a 1,048,576-token context window and up to 1M output tokens with long decode. Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.8 Live and the Gemini 3.1 Pro preview are also listed; you pick one with the model string in each request.

Recent changes

• Oct 27The Gemini API CLI (gemini-api) ships in beta: a stateless, zero-dependency command-line client for AI coding agents, scripts and CI pipelines, built on the Interactions API.
• Oct 13Gemini 4 Argon (gemini-4-argon) is generally available as Google's most capable model for complex coding, agentic, math and science tasks.
• Oct 8gemini-3.7-flash and gemini-3.5-flash are deprecated; requests are automatically routed to gemini-3.8-flash and gemini-3.6-flash.

Sources: Gemini Developer API pricing, Gemini API changelog, Gemini 4 Argon model page, Gemini API quickstart

Similar Tools

AI Models

Claude

Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.

AI Models

DeepSeek

Chinese lab shipping open-weight MoE models. The V4 family (previewed April 24, 2026) runs a 1M context on DeepSeek's API; R1 (2025) popularized open reasoning models. Low-cost API.

AI Models

G

GPT-5

OpenAI's GPT-5 model, released August 2025. Unified fast and reasoning modes in one model. Superseded by the GPT-6 family in September 2026 and now marked deprecated in the API.

AI Models

Grok

xAI's model family, now documented under the SpaceXSI (SpaceX Super Intelligence) name. Grok 4.7 (September 21, 2026) has a 500K context at $2/$6 per million tokens. OpenAI-compatible API.

More AI Models Tools

Claude

Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.

ChatGPT

OpenAI's chat app. As of October 2026 Free and Go run GPT-6 Luna; Plus ($20/mo) adds GPT-6.1 Sol and GPT-6 Astra. Agent mode, Codex, image generation, code interpreter.

OpenRouter

Unified API for hundreds of models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.