Felo API PlatformFelo API Platform
Back to models
Googlemessages

Gemini 2.5 Pro API

Google DeepMind's Gemini 2.5 Pro is a hybrid-reasoning, multimodal model with a 1 million token context window, built for advanced coding, agentic applications, and video understanding.

Gemini 2.5 Pro is Google DeepMind's flagship model, featuring a hybrid reasoning architecture that applies extended thinking before responding. It combines a 1 million token context window with multimodal understanding across text and video input, plus audio generation and real-time voice interaction. The model supports grounding with Google Search, parallel web search, code execution, and function calling, making it a versatile foundation for demanding workloads.

The model is positioned as Google's strongest offering for coding and world knowledge. It excels at web development and the creation of visually compelling web apps, agentic code applications, and code transformation and editing. Its video capabilities are state-of-the-art, including dynamic animation generation from videos with a single prompt. For complex prompts that require multiple rounds of strategizing and iterative solving, the extended thinking mode offers a structured path to higher-quality answers.

Gemini 2.5 Pro is well suited to software development, particularly web development, as well as building agentic applications and creative video work. It also handles natural real-time voice conversations and general-purpose AI tasks. Running at 110 tokens per second, it delivers strong reasoning performance on Math and STEM benchmarks and outperforms Gemini 2.5 Flash on all nine shared benchmarks.

Limited timeFree trial
Open Playground ↗Create API Key ↗Getting started →

Updated:

MODEL ID

gemini-2.5-pro
Context
1.049M
Max output
65.536K
Recommended API
messages
Input
text / image / file / audio / video
Output
text

Highlights

  • 1 million token context window
  • Hybrid reasoning with extended thinking
  • State-of-the-art video understanding
  • Strong web development and coding
  • Multimodal text and video input
  • Audio generation and real-time voice

Providers

Best price
4 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details
Uptime
$1.25$10$0.125$0.125
$0.625$5$0.0625$0.0625
$1.25$0.75$10$6$0.125$0.075$0.125$0.075
$2.25$18$0.225$0.225

What $10 buys

Input
8M tokens
Output
1M tokens

Estimated from current input and output prices, before discounts.

Benchmarks

  • VideoMME

    Video understanding benchmark score

    84.8%

  • LMArena

    First-place position on the leaderboard

    #1

  • BenchAlign

    Out of 100; ranked 104th out of 229 models

    49.26

Scores as published by the model provider.

Reasoning

Always enabled
Yes

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open PlaygroundCreate API Key
1

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"
2

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

gemini-2.5-pro

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "gemini-2.5-pro",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

3

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-2.5-pro",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription
modelstringgemini-2.5-proPublic model ID to call.
max_tokensinteger—Maximum generated tokens.
messagesarray—Conversation messages for Chat Completions.
seed———
toolsarray—Tool calling definitions following compatible schema.
top_p———
reasoning———
temperaturenumber—Controls response variety when supported.
tool_choicestring or object—Controls whether a tool should be called.
response_formatobject—Request structured output when supported.
include_reasoning———
structured_outputs———

Frequently asked questions

What is Gemini 2.5 Pro?

Gemini 2.5 Pro is Google DeepMind's flagship model, featuring a hybrid reasoning architecture that applies extended thinking before responding. It combines a 1 million token context window with multimodal understanding across text and video input, plus audio generation and real-time voice interaction. The model supports grounding with Google Search, parallel web search, code execution, and function calling, making it a versatile foundation for demanding workloads. The model is positioned as Google's strongest offering for coding and world knowledge. It excels at web development and the creation of visually compelling web apps, agentic code applications, and code transformation and editing. Its video capabilities are state-of-the-art, including dynamic animation generation from videos with a single prompt. For complex prompts that require multiple rounds of strategizing and iterative solving, the extended thinking mode offers a structured path to higher-quality answers. Gemini 2.5 Pro is well suited to software development, particularly web development, as well as building agentic applications and creative video work. It also handles natural real-time voice conversations and general-purpose AI tasks. Running at 110 tokens per second, it delivers strong reasoning performance on Math and STEM benchmarks and outperforms Gemini 2.5 Flash on all nine shared benchmarks.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.

What input modalities does Gemini 2.5 Pro support?

Gemini 2.5 Pro accepts text and video input. It also supports audio generation and real-time voice interaction.

How large is the context window?

Gemini 2.5 Pro offers a 1 million token context window.

What tasks is Gemini 2.5 Pro best suited for?

It is designed for complex prompts requiring multiple rounds of strategizing and iterative solving, complex reasoning in thinking mode, software development (especially web development), agentic applications, creative video work, and natural real-time voice conversations.

How does Gemini 2.5 Pro differ from Gemini 2.5 Flash?

Gemini 2.5 Pro outperforms Gemini 2.5 Flash on all nine shared benchmarks. It is positioned as Google's strongest model for coding and world knowledge.

Does Gemini 2.5 Pro support tool use?

Yes. It supports grounding with Google Search, parallel web search, code execution, and function calling.

Related models

Gemini 4 Carbon

Googlegemini-4-carbon

Gemini 4 Carbon is Google's strongest frontier model, built on Gemini 4 Argon for long-horizon agentic workflows, cybersecurity, scientific reasoning, and complex knowledge work.

Cybersecurity vulnerability discovery and patchingLong-horizon agentic workflowsLarge-scale codebase migrationsScientific reasoning and research

Context

1.049M

Max output

943.718K

Input tokens

$4 / 1M tokens

Output tokens

$20 / 1M tokens

Gemini 4 Carbon (batch)

Googlegemini-4-carbon:batch

Gemini 4 Carbon is Google's multimodal frontier model for long-horizon agentic work, with 1 million token context and adjustable reasoning effort.

Long-horizon agentic engineeringAdvanced coding and full-stack developmentDeep financial research and Excel modelsCyber defense and vulnerability discovery

Context

1.049M

Max output

943.718K

Input tokens

$2 / 1M tokens

Output tokens

$10 / 1M tokens

Gemini 4 Argon

Googlegemini-4-argon

Google's Gemini 4 Argon is a frontier model with a 1,048,576-token context window, multimodal input support, and top scores on 14 of 18 internal benchmarks.

Software engineering and codingFinance ledger reconciliationLegal case law reviewCybersecurity defense automation

Context

1.049M

Max output

943.718K

Input tokens

$4 / 1M tokens

Output tokens

$20 / 1M tokens

Gemini 3.8 Flash

Googlegemini-3.8-flash

Gemini 3.8 Flash is Google's most intelligent Flash model, a reasoning model with 1,000,000-token context and multimodal input for long-horizon agents and enterprise workflows.

Long-horizon software engineeringAutonomous agentsComplex enterprise workflowsMulti-step orchestration

Context

1.049M

Max output

65.536K

Input tokens

$1.5 / 1M tokens

Output tokens

$7.5 / 1M tokens

Gemma 4 26B A4B (free)

Googlegemma-4-26b-a4b-it:free

Gemma 4 26B A4B is an open-weight multimodal Mixture-of-Experts model from Google DeepMind with 26B total and 4B active parameters, a 256K token context, and support for text, image, and video input.

Coding assistance in IDEsAgentic workflows and tool useScientific and mathematical problem solvingDocument parsing and OCR

Context

262.144K

Max output

32.768K

Input tokens

$0 / 1M tokens

Output tokens

$0 / 1M tokens