Skip to content
Tier B — Production
Runs in:USMade in:United States
Google Gemini

Gemini 3.5 Flash-Lite

Tier B — Production · 1.048576M tokens

Tokonomix Editorial Team·Reviewed by Mes Kalkan··
Section 01

Speed analysis

Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.

P50 latency (median)P95 latency107 runs
275119321113029394710-2611-22ms
Section 02

Quality scores

How this model compares to the rest of the field on each prompt category, from a pairwise fit over the same prompts. The raw judge score sits underneath each number.

75%
Coding
judge mean 94
32%
Creative
judge mean 63
72%
Factual
judge mean 67
62%
Reasoning
judge mean 89

Win rate per category: how often this model beats a field-average model on a prompt from that category. 50% is average, not a failing grade. It is not a percentage of correct answers.

Section 03

Pricing

What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.

💰
API rates — Gemini 3.5 Flash-Lite
$0.4500 per 1M input tokens
$3.74 per 1M output tokens
≈ $0.0010 per typical conversation (800 tokens)
Input vs output price (per 1M tokens)
per 1M input tokens$0.4500
per 1M output tokens$3.74
Section 04

Tokens per second

Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.

Throughput (tokens / s)633 / avg 409
719163

Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.

Section 05

Capabilities

toolssource: seed-newest-generation-2026-09-30visionjson modepdf inputreasoningaudio inputjson schemaparallel toolsprompt cachingoutputTokenLimit: 65536max output tokens: 65536
Section 06

Availability

Availability

How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.

Last 7 days

100.0%

n=10

Last 30 days

100.0%

n=16

Median response time

2,209ms

n=16

Based on 390 measurements over the last 30 days.

Technical details

Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.

Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.

Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.

Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.

Total calls (30d)

16

OK responses (30d)

16

Total calls (7d)

10

OK responses (7d)

10

Section 07

Tokonomix benchmark verdicts

⚖️
Endorsed by 1 judge
Independent LLM judges evaluated this model on our weekly intelligence tests
claude-sonnet-4-582/100 · 25 runs
18 correct3 partial4 wrong72% accuracy
● 2026-11-22

Gemini 3.5 Flash-Lite maintains capabilities, still no benchmarks available

Gemini 3.5 Flash-Lite continues to offer an extensive set of capabilities including vision, audio input, PDF processing, reasoning, and multiple tool-calling features such as parallel tools and JSON schema support. The model also supports prompt caching and both JSON mode and JSON schema output formatting. However, for the second consecutive benchmark window, no performance metrics are available across any evaluation categories. This absence of data makes it impossible to assess the model's actual performance on standard benchmarks or compare it to other models in the Gemini family or broader market. The lack of benchmarks is particularly notable given the model's comprehensive feature set, which suggests it is positioned as a production-ready offering. Users considering this model should be aware that while the capability surface remains stable and robust, there is no empirical evidence available regarding its performance on tasks like reasoning, coding, mathematics, or general knowledge. Organizations requiring validated performance metrics for their use cases may need to conduct their own evaluations or await public benchmark results.

Quality

—

Latency p50

—

Test runs

0

✗ No performance data available
Last automated test
Nov 22, 2026 · 08:04 UTC · Speed benchmark
P50 latency
316 ms
P95 latency
346 ms
Errors
0 / 6 runs
Last reviewed by Tokonomix Team·November 22, 2026