Google · Llm model

Gemini 3.1 / 2.5

Three Gemini tiers, one API, transparent pricing.

Generate on Coinis Read the docs

One API key. Every model.

per 1m tokens
Example
AI text
Commercial use included Verified May 26, 2026 Outputs are yours No training on your data
Endpoints

Start building with Gemini 3.1 / 2.5.

One model. Three ways to call it. Same key, same bill.

IN

Llm

One call. Same key. Same bill.

$3.4 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$20.4 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$0.51 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$4.25 / 1m tokens

IN

Llm

One call. Same key. Same bill.

$2.13 / 1m tokens

OUT

Llm

One call. Same key. Same bill.

$17 / 1m tokens

Capabilities

What it does best.

Gemini AI capabilities

Context window

  • Gemini 2.5 Pro and Gemini 3.1 Pro Preview support up to 1,048,576 input tokens (~1M)[^1]
  • Gemini 2.5 Flash supports a 1.05M token context window[^4]

Modalities in

  • All three variants accept text, images, audio, video, and PDFs in a single API call[^2]

Modalities out

  • Text output only across all variants. No native image, audio, or video generation[^1]

Reasoning features

  • Gemini 2.5 Pro and Gemini 2.5 Flash include built-in chain-of-thought thinking[^3]
  • Gemini 3.1 Pro Preview adds a medium thinking level and measurable gains on SWE coding benchmarks[^5]
  • Gemini 2.5 Flash supports configurable thinking levels via max_tokens_for_reasoning[^3]
  • All variants support function calling, structured outputs, and code execution[^2]

Tooling

  • Search grounding (Google Search) available on paid tiers[^6]
  • URL context, context caching, and Batch API (50% cost reduction) available on paid tiers[^6]
  • Gemini 3.1 Pro Preview applies tiered pricing: prompts over 200K tokens are charged at a higher rate[^6]
API

Call Gemini 3.1 / 2.5 in three lines.

One key. One base URL. Same SDK shape you already use. 

# 1. set your key
export COINIS_API_KEY="sk_live_..."

# 2. call the model
curl https://api.app.coinis.com/v1/llm/generate \
  -H "Authorization: Bearer $COINIS_API_KEY" \
  -d '{"prompt":"neon city, rain, tracking shot"}'
import { Coinis } from "@coinis/sdk";
const coinis = new Coinis(process.env.COINIS_API_KEY);

const job = await coinis.llm.generate({
  model: "models/google/gemini-3-pro",
  prompt: "neon city, rain, tracking shot",
});
from coinis import Coinis
coinis = Coinis(os.environ["COINIS_API_KEY"])

job = coinis.llm.generate(
    model="models/google/gemini-3-pro",
    prompt="neon city, rain, tracking shot",
)
Response 
{
  "id": "gen_8fa2c1",
  "status": "succeeded",
  "model": "models/google/gemini-3-pro",
  "output": {
    "image_url": 
                "https://cdn.coinis.com/gen_8fa2c1.mp4"
              
              ,
    "format": "mp4"
  },
  "tokens_used": 10
}

Already on another provider's SDK? Change the host. Keep the call.

Pricing

Token pricing. No surprises.

One wallet across every model. No API accounts to juggle.

Gemini 3.1 / 2.5 · IN
34 tokens
per 1m tokens · $3.40
Frontier LLM
$3.40 / 1m tokens
One key. Every model. One invoice. 1 token = $0.10
1 1m tokens ≈ 34 tokens ($3.40)
Budget variant: IN · $0.51 / 1m tokens
Start free. 15 tokens a week.

No credit card.

Why pay through Coinis
  • One wallet for every model. No API keys. No separate bills.
  • Generate ads. Launch to Meta. Track in one place.
  • On-brand output from your Brand Profile.

1 token = $0.10 pay-as-you-go. Less on a plan.

Standard vs Fast

Pick the run for the job.

IN

Final renders, studios
Resolution —
Price $3.4 / 1m tokens

OUT

Rapid tests, high volume
Resolution —
Price $20.4 / 1m tokens
Use cases

Two buyers. One model.

For builders

Resell every model. One key. One bill.

Unified API across video, image, audio, and LLM.

Generate 500 variants overnight.

Async queue plus webhooks. Batch at scale.

White-label the output.

Ship it under your brand. Outputs are yours.

For creatives

Ship a Reel before lunch.

Prompt to platform-native clip in minutes.

Same product. Ten formats.

One generation, every aspect ratio.

Commercial UGC without a creator.

Authentic selfie-style ads, on brand.

Agentic workflows and multi-step tool orchestration Gemini 3.1 Pro Preview is built for structured planning, agentic coding, and workflow automation including financial modeling and multi-step task execution[^5]. It handles complex jobs where reliability across many tool calls matters most.

Long-context document and codebase analysis Gemini 2.5 Pro's 1M-token input window processes an entire codebase, legal document, or research corpus in one pass without chunking[^1]. Gemini 3.1 Pro Preview handles the same scale with added agentic reliability[^5].

Multimodal understanding Gemini 2.5 Pro accepts images, video frames, audio, and PDFs alongside text in one call[^1]. Use it for image-relevance scoring, video quality review, or cross-modal document analysis.

High-volume, low-latency production tasks Gemini 2.5 Flash is Google's most cost-efficient reasoning model[^2]. Run ad copy classification, light summarization, or high-frequency API calls at scale. Input tokens start at $0.51/1M on Coinis.

Complex coding, math, and STEM reasoning Gemini 2.5 Pro is purpose-built for advanced reasoning in code, mathematics, and scientific problems[^3]. Gemini 3.1 Pro Preview adds improved agentic reliability for multi-step coding jobs[^5].

Renders in seconds. Set a seed. Get the same frame back.

Outputs are yours. Sell them.

Safe for paid ads.

Your prompts are never used for training.

FAQ

Gemini 3.1 / 2.5 FAQs

How much does the Gemini API cost on Coinis vs. calling Google directly?

Coinis retail pricing is 1.7x Google direct rates. For Gemini 2.5 Flash, that means $0.51/1M input tokens and $4.25/1M output tokens on Coinis, versus $0.30/$2.50 on Google direct. For Gemini 2.5 Pro, Coinis charges $2.125/1M input and $17.00/1M output. You get a single unified API across all three Gemini variants plus other models, with no separate vendor account needed.

What is the difference between Gemini 3.1 Pro, Gemini 2.5 Pro, and Gemini 2.5 Flash?

Gemini 3.1 Pro Preview is Google's newest, highest-capability tier. It adds a medium thinking level, improved agentic reliability, and is best for complex multi-step workflows and long-context tasks. Gemini 2.5 Pro is the proven choice for vision-heavy reasoning, coding, and STEM. Gemini 2.5 Flash is the workhorse for high-volume, low-latency jobs where cost per call matters most.

Does Gemini 3.1 Pro Preview cost more for prompts over 200K tokens?

Yes. Google applies a surcharge for prompts exceeding 200K tokens. The Coinis retail rate for Gemini 3.1 Pro Preview at or under 200K tokens is $3.40/1M input and $20.40/1M output. Prompts over 200K are billed at a higher tier. See the official Google pricing docs for the exact over-200K rates, which sit above the base tier listed here.

Can I use Gemini for image, audio, or video input on Coinis?

Yes. All three Gemini variants accept text, images, audio, video, and PDFs as input in a single API call. Output is text only. No variant generates images, audio, or video natively. Image input is billed separately by the vendor. See the official docs at https://ai.google.dev/gemini-api/docs/pricing for input media rates.

Is Gemini 3.1 Pro Preview production-ready, or will it be deprecated?

Gemini 3.1 Pro Preview is a preview-stage model. It comes with more restrictive rate limits than stable releases and may change before reaching general availability. Google provides at least 2 weeks deprecation notice. For production workloads that need stability today, Gemini 2.5 Pro is the proven stable option.

Does Coinis support Gemini's Batch API discount and context caching?

Batch API (50% cost reduction) and context caching are available on paid tiers for supported Gemini variants including Gemini 2.5 Pro and Gemini 3.1 Pro Preview. These features are not available on the free tier. Contact Coinis or see the API docs for how to enable them in your integration.

What is the context window for Gemini on Coinis, and is it the same as Google direct?

Yes. Coinis passes through the full context window from Google direct. Gemini 2.5 Pro supports up to 1,048,576 input tokens. Gemini 3.1 Pro Preview and Gemini 2.5 Flash support approximately 1.05M tokens. Output is capped at 65,536 tokens for Gemini 2.5 Pro. No context is truncated on the Coinis side.

Related

Pair it with.

ChatGPT API / GPT-5.4

Model

Claude (Sonnet 4.6 / Opus 4.7 / Haiku 4.5)

Model

DeepSeek V4 Flash

Model

All LLM models

Catalog
Upscale this Edit a frame Add a voiceover

Start free

Your wallet. Every model. One call away.

Start free. 15 tokens a week. No card.

Generate on Coinis

No credit card.

Pricing and capabilities verified 2026-05-26. Read the docs .