Standard Compute
← All models
Gemini 3.8 Flash · Google

What does Gemini 3.8 Flash cost to run in a coding agent?

Gemini 3.8 Flash costs about $0.048 per average coding-agent request on our measured traffic, at list prices of $1.50 per million input and $7.50 per million output tokens. It gives strong general quality for its price and scores 41 on the Artificial Analysis Intelligence Index. (Source: Artificial Analysis (artificialanalysis.ai))

List prices: Gemini API pricing, checked 2026-10-13. Request costs: Standard Compute gateway data, 79,301 coding-agent requests from 75 users, Sep 13 to Oct 12, 2026. How we compute this

Run Gemini 3.8 Flash in your agent from $19/month

See plans

What Gemini 3.8 Flash costs per coding-agent request

Cost at list priceGemini 3.8 Flash
Prompt under 100K tokens50% of requests, 87% of input cached$0.023
Prompt of 100K to 272K39% of requests, 88% of input cached$0.058
Prompt over 272K tokens11% of requests, 86% of input cached$0.13
Average request$0.048
100 requests$4.83
Median session16 requests; a session ends after 10 idle minutes$0.65
A month of regular usemedian of 20 users active on 5+ days$73.52

Each logged request priced at the vendor's list rates for its own token counts, including cache reads and any higher rate for long prompts. Average output: 698 tokens per request.

What to watch for

These figures use Google's standard price from January 1, 2027. Until December 31, 2026 Google charges half ($0.75/$3.75), so today's bill is about $2.41 per 100 requests. Long agentic terminal work is its weak spot (19.1% on Terminal-Bench 4.0).

Where Gemini 3.8 Flash sits on the Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index bar chart with Gemini 3.8 Flash (high) highlighted, from artificialanalysis.ai, October 13, 2026
Artificial Analysis Intelligence Index v4.3.2, Gemini 3.8 Flash (high) highlighted, downloaded October 13, 2026. Source: Artificial Analysis (artificialanalysis.ai)

About Gemini 3.8 Flash

Gemini 3.8 Flash is Google's current Flash model, released September 2, 2026 with a 1M-token context and 64K output. It is strong for its price on general quality: #8 on LMArena's text board and 94.9 on Scale's SWE-Bench Pro V2, with 41 on the Artificial Analysis Intelligence Index at about 137 output tokens per second. Long agentic terminal work is its weak spot (19.1% on Terminal-Bench 4.0). The current $0.75/$3.75 price is introductory: Google lists $1.50/$7.50 from January 1, 2027.

Sources: Google announcement · Model card · Artificial Analysis · SWE-Bench Pro V2

Agents that run Gemini 3.8 Flash well

High-throughput agents and Gemini CLI users who want speed and big context.

Gemini 3.8 Flash FAQ

How much does Gemini 3.8 Flash cost per coding-agent request?
$0.048 on average at list price, $4.83 per 100 requests, and $0.65 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at Google's list rates; the median request sent 99,534 input tokens, 87% of input was read from cache, and requests returned 698 output tokens on average.
Does Gemini 3.8 Flash charge more for long prompts?
No. Gemini 3.8 Flash bills the same rate per token up to its 1M-token context window.
Is Gemini 3.8 Flash good for AI agents?
High-throughput agents and Gemini CLI users who want speed and big context. On our editorial scoring it rates 8.9/10 for agentic ability and 9.1/10 for output quality. #8 on LMArena text, ahead of several frontier models.
What is Gemini 3.8 Flash's context window?
Gemini 3.8 Flash has a 1.0M-token context window — large enough to hold sizeable codebases or document sets in a single run. Google is the maker.
Can I self-host Gemini 3.8 Flash?
No — Gemini 3.8 Flash is a proprietary, hosted-only model from Google. You access it through an API (e.g. OpenRouter) rather than running the weights yourself.
What are the downsides of Gemini 3.8 Flash?
The main trade-offs: Price doubles to $1.50/$7.50 on January 1, 2027; Weak on long terminal tasks (19.1% on Terminal-Bench 4.0). It's strongest for high-throughput agents and Gemini CLI users who want speed and big context.

Gemini 3.8 Flash compared

The agent matters as much as the model. Which agent gets the most out of Gemini 3.8 Flash? →

Every model on this page is included with Standard Compute

Standard Compute

Current frontier models Claude Opus 5.5 · Claude Sonnet 5.5

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. The most intelligence per dollar. One flat bill.

Plans from $19/mo · cancel anytime · 7-day fair refund

7-day fair refund No credit card needed Billing by Stripe1,800+ agent users