Gemini 3.1 Flash Lite · Google

What does Gemini 3.1 Flash Lite cost to run in a coding agent?

Gemini 3.1 Flash Lite costs about $0.0082 per average coding-agent request on our measured traffic, at OpenRouter's listed prices of $0.25 per million input and $1.50 per million output tokens. It scores 16 on the Artificial Analysis Intelligence Index, 43rd of the 48 models we track. Source: Artificial Analysis (artificialanalysis.ai)

List prices: OpenRouter listed price, 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 current Claude, GPT, Gemini and open models in your agent

Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.

See plans

What Flash Lite costs per coding-agent request

Cost at list price	Flash Lite
Prompt under 100K tokens50% of requests, 87% of input cached	$0.0040
Prompt of 100K to 272K39% of requests, 88% of input cached	$0.0099
Prompt over 272K tokens11% of requests, 86% of input cached	$0.022
Average request	$0.0082
100 requests	$0.82
Median session16 requests; a session ends after 10 idle minutes	$0.11
A month of regular usemedian of 20 users active on 5+ days	$12.53

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

Flash Lite benchmarks, speed and latency

Artificial Analysis	Value	Rank
Intelligence Index10 evaluations, 0 to 100	16	43 of 48
Terminal-Bench 4.0agentic coding in a terminal	0.5%	33 of 39
Output speedmedian	365 tokens/s	1 of 44
Time to first answer tokenincludes thinking time	5.0 s	4 of 44

Source: Artificial Analysis (artificialanalysis.ai). Measured variant: Gemini 3.1 Flash-Lite, speed on Google. Fetched October 13, 2026. Rank is among the models on this site, older versions included. Artificial Analysis runs Terminal-Bench 4.0 in its own setup, so its scores differ from the tbench.ai leaderboard.

About Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite is Google's budget model, released March 3, 2026 with a 1M-token context. It is the fastest model on this hub, at about 365 output tokens per second per Artificial Analysis, but it scores 16 on the Artificial Analysis Intelligence Index and 0.5% in its Terminal-Bench 4.0 run, so it suits classification, extraction and other simple steps rather than agent loops. GPT-6 Luna costs about half as much per request in our measurements ($0.0041 vs $0.0082) and scores 38.

Sources: Artificial Analysis

Gemini 3.1 Flash Lite FAQ

How much does Gemini 3.1 Flash Lite cost per coding-agent request?

$0.0082 on average at OpenRouter's listed price, $0.82 per 100 requests, and $0.11 for a median 16-request session. That is 79,301 real coding-agent requests (Sep 13 to Oct 12, 2026) priced at OpenRouter's listed 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 3.1 Flash Lite charge more for long prompts?

No. Gemini 3.1 Flash Lite bills the same rate per token up to its 1M-token context window.

How fast is Gemini 3.1 Flash Lite?

Artificial Analysis measures Gemini 3.1 Flash-Lite at 365 output tokens per second, with 5.0 seconds to the first answer token, thinking time included, on Google's API. Source: Artificial Analysis (artificialanalysis.ai).

Is Gemini 3.1 Flash Lite good for AI agents?

Simple, high-volume steps such as classification and extraction. On our scoring, which is calibrated to public benchmarks, it rates 4.6/10 for agentic ability and 4.3/10 for output quality. 1M context at a low price.

What is Gemini 3.1 Flash Lite's context window?

Gemini 3.1 Flash Lite 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 3.1 Flash Lite?

No. Gemini 3.1 Flash Lite is a proprietary, hosted-only model from Google. You access it through an API, such as OpenRouter, rather than running the weights yourself.

What are the downsides of Gemini 3.1 Flash Lite?

The main trade-offs: Not suited to multi-step agent work (0.5% in Artificial Analysis's Terminal-Bench 4.0 run); GPT-6 Luna costs about half as much per request and scores far higher. It's strongest for simple, high-volume steps such as classification and extraction.