Google · Efficient
Gemini Flash Lite Latest
Compatibility alias that routes to the newest version of Gemini Flash Lite. Currently routes to Gemini 3.5 Flash Lite.
- Reasoning
- Tools
- Vision
- Structured output
- PDF input
- Audio input
- Video input
- Input
- Text, Images, Video, Audio
- Output
- Text
- Reasoning effort
- minimal · low · medium · high
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.30
- Output
- $2.50
- Cache read
- $0.03
- Cache write
- $0.0833
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 65.5K
Side by side
Gemini Flash Lite Latest compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Gemini Flash Lite LatestGoogleThis model | Kimi K2 ThinkingMoonshotRemove | |
|---|---|---|
| Provider | Moonshot | |
| Discovery tier | Efficient | Open weights |
| Added | Mar 29, 2026 | Nov 6, 2025 |
| Limits | ||
| Context window | 1.05MBest | 262.14K |
| Max output | 65.54K | 98.3KBest |
| Average output | — | 1.9K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.30Best | $0.60 |
| Output | $2.50 | $2.50 |
| Cache read | $0.03Best | $0.15 |
| Cache write | $0.0833 | — |
| Performance | ||
| Throughput | — | 77.5 tok/s |
| Time to first token | — | 5.1 s |
| Request success (24h) | 99.8%Best | 99.6% |
| Benchmark indexes | ||
| Intelligence Index | 22.2Best | 22.0 |
| Coding Index | 49.3 | — |
| Math Index | — | 94.7 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | No |
| Structured output | Yes | Yes |
| PDF input | Yes | No |
| Audio input | Yes | No |
| Video input | Yes | No |
| Reasoning effort | minimal, low, medium, high | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Gemini Flash Lite Latest
- Kimi K2 Thinking
Intelligence Index
- Gemini Flash Lite Latest22.2
- Kimi K2 Thinking22.0
Gemini Flash Lite Latest: Better than 53% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Gemini Flash Lite Latest: 49.3
- Kimi K2 Thinking: —
Math Index
Composite of the math evaluations
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 94.7
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Gemini Flash Lite Latest: 25.0%
- Kimi K2 Thinking: —
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Gemini Flash Lite Latest: 3.3%
- Kimi K2 Thinking: —
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- Gemini Flash Lite Latest: 0.0%
- Kimi K2 Thinking: —
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Gemini Flash Lite Latest: 650 Elo
- Kimi K2 Thinking: —
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Gemini Flash Lite Latest: 985 Elo
- Kimi K2 Thinking: —
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Gemini Flash Lite Latest: 13.6%
- Kimi K2 Thinking: —
AA-LCRv1.1
Reasoning across long documents
- Gemini Flash Lite Latest: 76.0%Top
- Kimi K2 Thinking: 72.0%
MLCR-AA
Long-context reasoning over medical records
- Gemini Flash Lite Latest: 10.6%
- Kimi K2 Thinking: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Gemini Flash Lite Latest: 18.8%
- Kimi K2 Thinking: 23.8%Top
GPQA Diamond
Graduate-level science questions
- Gemini Flash Lite Latest: 83.8%Top
- Kimi K2 Thinking: 83.8%Top
MMLU-Pro
Multi-subject knowledge and reasoning
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 84.8%
IFBench
Following precise output instructions
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 68.1%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Gemini Flash Lite Latest: 1.0%
- Kimi K2 Thinking: —
SciCode
Scientific computing in Python
- Gemini Flash Lite Latest: 41.3%
- Kimi K2 Thinking: —
LiveCodeBench
Recent competitive programming problems
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 85.3%
Math
AIME 2025
Competition mathematics, 2025 problems
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 94.7%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 31.1%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Gemini Flash Lite Latest: —
- Kimi K2 Thinking: 93.0%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Gemini Flash Lite Latest: 76.0%Top
- Kimi K2 Thinking: 72.0%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 21.0%
- About $0.24 per 1M input tokens with caching
- Request success (24h)
- 99.9%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-flash-lite-latest",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="google/gemini-flash-lite-latest",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Related models
Other Google models, starting with the same family.