Google1M (2M experimental) contextgemini-2-5-pro

Gemini 2.5 Pro

Google's flagship — 1M-token context, strong multimodal, sharp on math

Gemini 2.5 Pro was Google's flagship through early 2026 — 1M-token context standard, strong multimodal (vision, audio, video), and sharp on math + code. Still production-supported, but now superseded by Gemini 3.5 Flash (live since May 19, 2026) on agentic + coding benchmarks and by the upcoming Gemini 3.5 Pro on hardest reasoning + long-context recall. See the Gemini 3.5 Flash page for the current generation.

Pricing

Rate	List price	Anvat effective	Savings
Input (≤200K)	$1.25	$0.88	30%
Output (≤200K)	$10.00	$7.00	30%
Input (>200K)	$2.50	$1.75	30%
Output (>200K)	$15.00	$10.50	30%
Cache read	$0.31	$0.22	29%
All prices per million tokens (MTok). List = provider direct. Anvat effective = 30% discount applied.

Pricing verified 2026-06 · See full Anvat pricing

Strengths

1M-token context standard — no separate extended tier required
Strong on math (top-tier on MATH benchmark)
Native multimodal — text, image, audio, video in a single model
Excellent at structured-output generation (JSON, XML, code)
Cheapest input price among frontier models at $1.25/MTok

Where it underperforms

Coding agent reliability still behind Opus 4.8 (SWE-bench)
Less mature tool-use ecosystem outside Vertex / Google AI Studio
Output speed slower than Claude Sonnet on long generations
Less aggressive prompt caching than Anthropic

Use cases this model is the right pick for

Long-document analysis where 200K isn't enough
Multimodal pipelines (transcribe + analyse + summarise)
Math-heavy reasoning and tutoring
Cheap input-heavy workflows where input >> output tokens
Google Cloud-native applications

Benchmarks

reasoning
Context window
1M tokens standard
math
MATH / math reasoning
Top-tier
vision
Multimodal (video)
Industry-leading

Benchmark numbers self-reported by provider; verify against the latest publisher documentation before quoting.

Quickstart

Same wire format as direct provider APIs — your existing SDK code keeps working. Point at api.anvat.app/v1 and use your Anvat key.

// Gemini via OpenAI-compatible endpoint on Anvat
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.anvat.app/v1",
  apiKey: process.env.ANVAT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gemini-2-5-pro",
  messages: [
    {
      role: "user",
      content: "Summarize this 500-page PDF I've attached as a chronological timeline.",
    },
  ],
});

Try Gemini 2.5 Pro — 30% off list

Same model, same quality, same wire format — at the discounted Anvat effective rate. $2 free credit on signup, no card required.

Get a key →