LLM API pricing

Deep Research Preview (Apr-21-2026) API pricing: cheapest provider

2 providers sell Deep Research Preview (Apr-21-2026). Google Gemini API is cheapest, and listed prices are close.

  • Cheapest$4.50per 1M · Google Gemini API
  • Input · output$2.00 / $12.00per 1M tokens
  • Price gap1.0×across 2 providers
  • Context1Mmax tokens
$4.50 Google Gemini APIclose prices$4.50 Google Cloud Vertex AI
Compare all 2 providers
Already paying for Deep Research Preview (Apr-21-2026)? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Nov 14, 2026 · How we collect and rank prices

Ranked for your volume

Deep Research Preview (Apr-21-2026) monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

More requirements: caching, context, features, provider

Share this page URL to keep your scenario. 2 of 2 providers meet these assumptions.

Cheapest provider for your volume

Google Gemini API

Same price at all 2 options

$180.00estimated / month
ProviderEstimated / monthInput / 1MOutput / 1MCached input / 1MContext
1
$180.00$2.00$12.00Not listed1M
$180.00$2.00$12.00$0.20Not listed

Order depends on listed price for your volume only. No provider pays for its position.

What this estimate leaves out

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Price history

The cheapest price has not changed since tracking started on Sep 28, 2026: $4.50 per 1M tokens at Google Gemini API. All price changes

Switch to the cheapest provider

Switch to Google Gemini API

Already using the OpenAI SDK? Change the base URL, key and model name.

Show the code
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://generativelanguage.googleapis.com/v1beta/openai",
    api_key=os.environ["GEMINI_API_KEY"],
)
response = client.chat.completions.create(
    model="deep-research-preview-04-2026",
    messages=[{"role": "user", "content": "Hello"}],
)
Base URL from Google Gemini API's API docs, model name from the open pricing datasets. Check the model page in Google Gemini API's docs before you switch production traffic.

Compare Deep Research Preview (Apr-21-2026) with another model

Or compare against any other model

Selected modelDeep Research Preview (Apr-21-2026)

Before you pick a provider

1 of 2 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.