Google
·Released on May 19, 2026Gemini 3.5 Flash API Benchmarks, Pricing & Provider Data
Compare Gemini 3.5 Flash with another model
Choose a model to open its comparison page.
LLM
Gemini 3.5 Flash benchmark, API pricing, and provider data cover 398 API providers, with prices starting at $0.0027/request. Gemini 3.5 Flash free API options are available from 3 providers. The page also shows measured API speed and first-token latency.
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel age...
Quality
#25of 100
66.0
LMSpeed score
Speed
#9of 77
384char/s
39.32 s
Cost
#135of 181
$0.0027/ 1M · 8:1 in:out
$0.0004 in · $0.0023 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 7 / 8
- Methodology
- V3.0
#1Agents60.6RatedGlobal rank #104/4 Measured dimensions
80% interval: 55.1–66.2
planning56.6
deep_planning · gert_labs
tool use63
mcp_atlas · mcp_atlas / tau · tau2_bench / toolathlon · toolathlon
environment execution63
enterprise_ops_gym · aa_enterprise_ops_gym / gdpval_aa · benchlm_agentic_gdpval_aa / osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability60
apex_agents · apex_agents_aa / researchclaw · research_claw_bench
#2Multimodal56.3Estimated2/4 Measured dimensions
80% interval: 44.4–68.2
perception ocrPrior only
document spatial51.8
charxiv · charxiv
visual reasoning60.8
mmmu_pro · mmmu_pro
video actionPrior only
#3Coding55.8RatedGlobal rank #143/4 Measured dimensions
80% interval: 46.9–64.7
code generation61.1
scicode · scicode
repository engineering52.3
swe_pro · swe_pro / vibecode · vibe_code_bench
debugging testingPrior only
tooling quality54.1
terminalbench · benchlm_coding_terminal_bench2
#4Math55.1Provisional1/4 Measured dimensions
80% interval: 39.1–71.2
foundational mathPrior only
competition mathPrior only
proof frontier55.1
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#5Instruction following54.8Provisional1/4 Measured dimensions
80% interval: 38.8–70.8
constraint followingPrior only
structured outputPrior only
novel instruction generalization54.8
ifbench · aa_if_bench
long multiturn instructionPrior only
#6Knowledge53.9Provisional1/4 Measured dimensions
80% interval: 39.9–67.9
broad knowledge53.9
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#7Reasoning53.4RatedGlobal rank #303/4 Measured dimensions
80% interval: 45.0–61.8
abstract logic51.3
arc_agi · arc_agi2
scientific causal62
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraintsPrior only
evidence verification46.9
lcr · lcr / mrcr · mrcr1m
No data:Multilingual
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
INPUT
1.0Mtokens
≈ 1.3K pages of text
OUTPUT
65.5Ktokens
8K128K1M4M
1.0M
Features
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 1, 2026Overall
undefined metric} other undefined metrics}}
Overall score66.0#25 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing
undefined metric} other undefined metrics}}
Input price$1.50/M#135 / 181Output price$9.00/M#138 / 181
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score60.6#1080% interval55.1–66.24/4 Measured dimensionsAgentic score77.9#21 / 69Terminal-Bench 2.076.2#12 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition56.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.89 · q 1.00
Tool use63
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z 1.09 · q 1.00
tau · tau2_bench · z 0.65 · q 1.00
toolathlon · toolathlon · z 0.86 · q 1.00
Environment & long-horizon execution63
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
enterprise_ops_gym · aa_enterprise_ops_gym · z 1.03 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z 0.52 · q 1.00
osworld · os_world_verified · z 0.53 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 0.88 · q 1.00
Recovery & completion reliability60
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
apex_agents · apex_agents_aa · z 1.24 · q 1.00
researchclaw · research_claw_bench · z 0.00 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score55.8#1480% interval46.9–64.73/4 Measured dimensionsSciCode53.1%#18 / 206Coding score54.4#35 / 81
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation61.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · scicode · z 1.36 · q 1.00
Repository engineering52.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_pro · swe_pro · z -0.31 · q 1.00
vibecode · vibe_code_bench · z 0.82 · q 1.00
Debugging & testingPrior only
Tool-assisted development & quality54.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
terminalbench · benchlm_coding_terminal_bench2 · z 0.55 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score53.4#3080% interval45.0–61.83/4 Measured dimensionsGPQA92.2%#16 / 213HLE42.7%#16 / 210
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logic51.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
arc_agi · arc_agi2 · z 0.00 · q 1.00
Scientific & causal reasoning62
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.68 · q 1.00
gpqa · gpqa · z 1.20 · q 1.00
hle · hle · z 0.98 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification46.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z -0.04 · q 1.00
mrcr · mrcr1m · z -0.92 · q 0.75
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score53.980% interval39.9–67.91/4 Measured dimensionsKnowledge score60.4#49 / 69Artificial Analysis Intelligence Index50.2#22 / 111
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge53.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 0.85 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z -0.41 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#22
Score50.2
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence4
AA-Omniscience Hallucination Rate
LMSpeed rank#66
Score60.7
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence4
AA-Omniscience IndexV3 evidence
LMSpeed rank#13
Score21.2
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence4
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score55.180% interval39.1–71.21/4 Measured dimensionsMath score55.9#33 / 62FrontierMath v2 (Tiers 1-3)39.0#12 / 47
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs55.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 0.53 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.41 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#12
Score39.0
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence4
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#14
Score14.6
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence4
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Score56.380% interval44.4–68.22/4 Measured dimensionsMultimodal Grounded score80.6#7 / 44CharXiv84.2#10 / 29
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understanding51.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
charxiv · charxiv · z 0.36 · q 1.00
Visual reasoning60.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmmu_pro · mmmu_pro · z 1.37 · q 1.00
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score54.880% interval38.8–70.81/4 Measured dimensionsInstruction Following score82.4#18 / 25IFBench76.3#9 / 14
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization54.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.37 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
7 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google AI Studio google-ai-studio/flex | $0.750/M | $4.50/M | 100% | — | — | undefined tokens / undefined tokens |
Google google-vertex/global/priority | $2.70/M | $16.20/M | 100% | — | — | undefined tokens / undefined tokens |
Google AI Studio google-ai-studio/priority | $2.70/M | $16.20/M | 100% | — | — | undefined tokens / undefined tokens |
Google google-vertex/global | $1.50/M | $9/M | 99.2% | — | — | undefined tokens / undefined tokens |
Google AI Studio google-ai-studio | $1.50/M | $9/M | 98.5% | — | — | undefined tokens / undefined tokens |
Google google-vertex/global/flex | $0.750/M | $4.50/M | — | — | — | undefined tokens / undefined tokens |
Google google-vertex/us | $1.65/M | $9.90/M | — | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Gemini 3.5 Flash API pricing across 395 providers. Prices range from $0.0027/request to $1200.00/M. PoloAPI offers the lowest rate at $0.0027/request. 3 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gemini-3.5-flash | gemini-cli | -93%$0.103/M Cache read$0.010/M | -93%$0.616/M | — | — | — | |
L1 100% | gemini-3.5-flash | gemini-officially | $1.50/M Cache read$0.150/M | $9.00/M | — | — | — | |
L1 100% | gemini-3.5-flash-nothinking | gemini_cli | -50%$0.750/M | -50%$4.50/M | — | — | — | |
L1 100% | gemini-3.5-flash | gemini_cli | -50%$0.750/M | -50%$4.50/M | — | — | — | |
L1 100% | gemini-3.5-flash | default | -86%$0.205/M | -86%$1.23/M | — | — | — | |
L1 100% | gemini-3.5-flash-high | default | $10.27/M | $30.82/M | — | — | — | |
L1 100% | gemini-3.5-flash-low | default | $10.27/M | $30.82/M | — | — | — | |
L1 100% | gemini-3.5-flash | 特供-gemini45折 | -86%$0.205/M Cache read$0.021/M | -86%$1.23/M | — | — | — | |
L1 100% | gemini-3.5-flash | default | $1.50/M Cache read$0.150/M | $9.00/M | — | — | — | |
L1 100% | gemini-3.5-flash | default | $4.50/M | $27.00/M | — | — | — | |
兔子API Free | L1 100% | gemini-3.5-flash | 官方优惠 | Free | Free | — | — | — |
L1 100% | gemini-3.5-flash-c | default | $0.014/request | - | — | — | — | |
L1 100% | gemini-3.5-flash | default | $1.50/M Cache read$0.150/M | $9.00/M | — | — | — | |
L1 100% | gemini-3.5-flash | daily-gemini | -85%$0.225/M Cache read$0.022/M | -85%$1.35/M | — | — | — | |
L1 100% | gemini-3.5-flash-high | daily-gemini | -85%$0.225/M Cache read$0.022/M | -85%$1.35/M | — | — | — | |
L1 100% | gemini-3.5-flash-low | daily-gemini | -85%$0.225/M Cache read$0.022/M | -85%$1.35/M | — | — | — | |
L1 100% | gemini-3.5-flash | gemini-个人版 | -83%$0.249/M | -83%$1.49/M | — | — | — | |
L1 100% | gemini-3.5-flash-low | gemini | -75%$0.375/M | -75%$2.25/M | — | — | — | |
L1 100% | gemini-3.5-flash | gemini | -75%$0.375/M Cache read$0.037/M | -75%$2.25/M | — | — | — | |
L1 100% | gemini-3.5-flash | gemini | -73%$0.411/M Cache read$0.041/M | -73%$2.47/M | — | — | — |
Showing 20 model IDs of 147.
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
125 shared providers
Gemini 3.1 Pro
gemini-3-1-pro
Google Gemini 3.1 Pro is a Gemini 3 series model with advanced multimodal reasoning, long-context support, and strong performance on coding and analytical tasks.
123 shared providers
Claude Sonnet 4.6
claude-sonnet-4-6
Anthropic Claude Sonnet 4.6 extends the Sonnet line with improved tool use, coding reliability, and long-context performance for everyday production workloads.
119 shared providers
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
118 shared providers
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
116 shared providers
Claude Opus 4.7
claude-opus-4-7
Anthropic Claude Opus 4.7 targets frontier-level analysis, complex coding, and autonomous workflows that require deep multi-step reasoning.
115 shared providers
Frequently Asked Questions
- What benchmark data does Gemini 3.5 Flash include?
- LMSpeed shows Gemini 3.5 Flash benchmark context, API price, output speed, first-token latency, and provider data across 398 providers when those signals are available.
- What is the Gemini 3.5 Flash API price?
- Gemini 3.5 Flash has pricing from 398 providers, ranging from $0.0027/request to $1200.00/M. PoloAPI has the lowest listed price.
- What does the Gemini 3.5 Flash API pricing table include?
- The Gemini 3.5 Flash API pricing table compares 398 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Gemini 3.5 Flash API pricing?
- PoloAPI currently has the lowest listed Gemini 3.5 Flash price at $0.0027/request across 398 providers.
- Can I compare Gemini 3.5 Flash API price and speed together?
- Yes. LMSpeed shows Gemini 3.5 Flash API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Gemini 3.5 Flash API free?
- Yes, Gemini 3.5 Flash free API options are available through 3 providerundefined other undefined} on LMSpeed, including 兔子API, Moyanjdc API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Gemini 3.5 Flash free API access?
- LMSpeed currently lists 3 free API providerundefined other undefined} for Gemini 3.5 Flash: 兔子API, Moyanjdc API, 兔子API. Check each provider row before using it because free tier limits can change.