Gemini 2.5 Pro Preview 06-05 API

google/gemini-2.5-pro-preview
Gemini 2.5 Pro Preview 06-05 on AIMLAPI.
Context
1.05M tokens
Input
$1.71925 / 1M tokens
Output
$13.754 / 1M tokens

How to use Gemini 2.5 Pro Preview 06-05 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-2.5-pro-preview.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-2.5-pro-preview",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-2.5-pro-preview",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-2.5-pro-preview","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Gemini 2.5 Pro Preview 06-05 API Pricing

TypePrice
Input
$1.71925 / 1M tokens
Output
$13.754 / 1M tokens
Cached input
$0.171925 / 1M tokens

Gemini 2.5 Pro Preview 06-05 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
LiveCodeBench
69%
Contamination-free competitive programming problemsSourceJuly 12, 2026
SWE-bench Verified
59.6%
Resolving verified real GitHub issuesSourceJuly 12, 2026
AIME 2025
88%
Competition mathematics (AIME), 2025SourceJuly 12, 2026
GPQA Diamond
86.4%
Google-proof graduate science questions (hardest subset)SourceJuly 12, 2026
Intelligence
15
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
46.7
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Gemini 2.5 Pro Preview 06-05 vs other models

ModelInputOutputContextBest for
$1.71925 / 1M tokens
$13.754 / 1M tokens
1.05M tokens
Reasoning + agents
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Gemini 2.5 Pro Preview 06-05 has a 1,048,576 tokens context window and can return up to 65,536 tokens.

Gemini 2.5 Pro Preview 06-05 takes image, text as input and returns text.

Use google/gemini-2.5-pro-preview as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Gemini 2.5 Pro Preview 06-05 is priced at input $1.71925 / 1M tokens, output $13.754 / 1M tokens, cached input $0.171925 / 1M tokens.

Yes, Gemini 2.5 Pro Preview 06-05 can stream responses as they are generated.

Yes, Gemini 2.5 Pro Preview 06-05 accepts image input alongside text.

Gemini 2.5 Pro Preview 06-05 was built by Google.

Yes, it supports function calling, parallel tool calls, and structured outputs, along with reasoning and web search.

Start building with Gemini 2.5 Pro Preview 06-05

Get API Key
1000+ models, one API.