Gemini 2.0 Flash

Name: Gemini 2.0 Flash
Author: Google DeepMind

Released

2025-01-30

Last refreshed

2026-06-29

Status

Researched 38d ago

DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Gemini 2.0 Flash is a legacy integration reference; evaluate Gemini 3.5 Flash before starting new work.

Use it for

Teams maintaining an existing integration
Workloads that can use a 2m context window
Buyers comparing 3 tracked provider routes

Do not use it for

New production launches

Specifications

Family: Gemini 2.0
Released: 2025-01-30
Context: 2m
Knowledge cutoff: 2025-04
Openness: Proprietary
License: Gemini Terms of ServiceCommercial use: conditional

Created by

Google DeepMind

Pioneering artificial intelligence research.

London, United Kingdom

Founded 2014

Website

Pricing

Output / 1M

$0.400

Input / 1M

$0.100

Cheapest of 4 routes · OpenRouter

Providers(4)

OpenRouter Google AI Studio GCP Vertex AI Vercel AI Gateway

View 4 provider routes

This model is deprecated. Google DeepMind recommends switching to Gemini 3.5 Flash.

About

Google Gemini 2.0 Flash is deprecated and scheduled to shut down on June 1, 2026. Use a newer Gemini model such as Gemini 3.5 Flash for current integrations; official Gemini API pricing still lists $0.10 input / $0.40 output per 1M text, image, or video tokens before batch discounts.

Gemini 2.0 Flash is a proprietary model in the Gemini 2.0 family. The structured metadata tracks a 2m-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through OpenRouter, Google AI Studio, GCP Vertex AI, and 1 more, with the cheapest tracked route listed at $0.1 input and $0.4 output per 1M tokens. Headline tracked benchmarks include MMLU PRO 77.9.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 4

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Batch in / out	Cache	Route
OpenRouter	$0.100	$0.400	-	-	Serverless
GCP Vertex AI	$0.150	$0.600	$0.075 / $0.300	-	Serverless
Vercel AI Gateway	$0.150	$0.600	-	read $0.025	Serverless

Available via routers & gateways(13)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSGoogle AI StudioGCP Vertex AI

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughGoogle AI StudioGCP Vertex AI

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionGoogle AI StudioGCP Vertex AI

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeGoogle AI StudioGCP Vertex AI

Helicone

Gateway

Observability-first AI gateway with routing, caching, rate limiting, and request tracing; Apache 2.0 open-source core with a managed hosted tier for logging and analytics.

SubscriptionGoogle AI StudioGCP Vertex AI

Kong AI Gateway

Gateway

Multi-LLM AI gateway built on Kong Gateway 3.x, adding semantic routing, load balancing, guardrails, and MCP traffic analytics as plugins over Kong's existing API management platform.

SubscriptionGoogle AI StudioGCP Vertex AI

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Benchmark peer barsfor Classification

MMLU PRORank 61 of 104

Gemini 3 Pro

91.8

Gemini 3.1 Pro Preview

91.0

Qwen3.7-Max

89.6

Claude Opus 4.6

89.1

Gemini 2.0 Flashcurrent

77.9

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.