Google
·Released on Feb 19, 2026Gemini 3.1 Pro API Benchmarks, Pricing & Provider Data
Compare Gemini 3.1 Pro with another model
Choose a model to open its comparison page.
LLM
Gemini 3.1 Pro benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0050/request. Gemini 3.1 Pro free API options are available from undefined provider} other undefined providers}}. The page also shows measured API speed and first-token latency.
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.
Quality
#27of 112
67.0
LMSpeed score
Speed
149char/s
16.52 s
Cost
$0.0050/ 1M · 8:1 in:out
$0.0008 in · $0.0042 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 8 / 8
- Methodology
- V3.0
#1Multilingual69.3Provisional1/4 Measured dimensions
80% interval: 52.2–86.3
cross language understanding69.3
global_mmlu · aa_global_mmlu_lite
multilingual generationPrior only
reasoning transferPrior only
low resource robustnessPrior only
#2Reasoning57.4RatedGlobal rank #113/4 Measured dimensions
80% interval: 48.7–66.1
abstract logic51.7
arc_agi · arc_agi2
scientific causal63.3
critpt · critpt / gpqa · aa_gpqa_diamond / hle · aa_hle / hle · hle_no_tools
multistep constraintsPrior only
evidence verification57.2
lcr · lcr
#3Coding57.2Estimated2/4 Measured dimensions
80% interval: 46.5–67.9
code generation62.7
livecodebench · live_code_bench_pro / scicode · aa_sci_code
repository engineering51.7
react_native_bench · react_native_evals / vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#4Knowledge57Provisional1/4 Measured dimensions
80% interval: 42.0–72.1
broad knowledgePrior only
professional knowledge57
healthbench · health_bench_hard / medxpert · med_xpert_qa_text
factualityPrior only
retrieval open bookPrior only
#5Instruction following55.3Provisional1/4 Measured dimensions
80% interval: 39.3–71.3
constraint followingPrior only
structured outputPrior only
novel instruction generalization55.3
ifbench · aa_if_bench
long multiturn instructionPrior only
#6Multimodal55.1RatedGlobal rank #24/4 Measured dimensions
80% interval: 48.5–61.7
perception ocr53
simplevqa · simple_vqa
document spatial47.8
charxiv · charxiv
visual reasoning64.1
erqa · erqa / medxpert · med_xpert_qa_mm / mmmu_pro · mmmu_pro
video action55.5
screenspot · screen_spot_pro
#7Math54.6Provisional1/4 Measured dimensions
80% interval: 38.6–70.7
foundational mathPrior only
competition mathPrior only
proof frontier54.6
frontiermath · frontier_math_v2_tier4 / frontiermath · frontier_math_v2_tiers13
applied tool mathPrior only
#8Agents50.2RatedGlobal rank #384/4 Measured dimensions
80% interval: 44.0–56.3
planning54
deep_planning · gert_labs
tool use56
tau · tau2_bench
environment execution44.9
deep_search_qa · deep_search_qa / gdpval_aa · benchlm_agentic_gdpval_aa
recovery reliability45.9
apex_agents · apex_agents_aa / claw_eval · claw_eval / researchclaw · research_claw_bench
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 13, 2026Overall
undefined metric} other undefined metrics}}
Overall score67.0#27 / 112
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score50.2#3880% interval44.0–56.34/4 Measured dimensionsAgentic score72.8#28 / 77Claw-Eval57.8#16 / 27
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decomposition54
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z 0.55 · q 1.00
Tool use56
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z 0.70 · q 1.00
Environment & long-horizon execution44.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_search_qa · deep_search_qa · z -0.69 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z -0.65 · q 1.00
Recovery & completion reliability45.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
apex_agents · apex_agents_aa · z 0.44 · q 1.00
claw_eval · claw_eval · z -0.29 · q 1.00
researchclaw · research_claw_bench · z -1.64 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score57.280% interval46.5–67.92/4 Measured dimensionsCoding score74.3#7 / 87LiveCodeBench Pro82.9#2 / 4
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Code generation62.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · live_code_bench_pro · z 0.54 · q 0.50
scicode · aa_sci_code · z 1.52 · q 1.00
Repository engineering51.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
react_native_bench · react_native_evals · z 0.10 · q 1.00
vibecode · vibe_code_bench · z 0.27 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score57.4#1180% interval48.7–66.13/4 Measured dimensionsReasoning score50.6#60 / 67ARC-AGI-277.1#8 / 19
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Abstract logic51.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
arc_agi · arc_agi2 · z 0.15 · q 1.00
Scientific & causal reasoning63.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.73 · q 1.00
gpqa · aa_gpqa_diamond · z 1.42 · q 1.00
hle · aa_hle · z 1.05 · q 1.00
hle · hle_no_tools · z 0.30 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification57.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.62 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score5780% interval42.0–72.11/4 Measured dimensionsKnowledge score79.2#20 / 83GPQA-D94.3#3 / 32
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledgePrior only
Professional knowledge57
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
healthbench · health_bench_hard · z -1.20 · q 1.00
medxpert · med_xpert_qa_text · z 2.02 · q 0.50
FactualityPrior only
Retrieval & open-book usePrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Artificial Analysis Intelligence Index
LMSpeed rank#48
Score30.4
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#76
Score50.9
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score54.680% interval38.6–70.71/4 Measured dimensionsMath score54.3#35 / 63FrontierMath v2 (Tiers 1-3)36.9#15 / 47
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofs54.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
frontiermath · frontier_math_v2_tier4 · z 0.58 · q 1.00
frontiermath · frontier_math_v2_tiers13 · z 0.36 · q 1.00
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
FrontierMath v2 (Tiers 1-3)V3 evidence
LMSpeed rank#15
Score36.9
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
FrontierMath v2 (Tier 4)V3 evidence
LMSpeed rank#14
Score16.7
Sourcebenchlm.ai
UpdatedSep 13, 2026
Confidence3
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Score69.380% interval52.2–86.31/4 Measured dimensionsAA Global-MMLU-Lite93.2#1 / 5
Multilingual
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Cross-language understanding69.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
global_mmlu · aa_global_mmlu_lite · z 2.79 · q 0.63
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Multimodal
V3.0undefined metric} other undefined metrics}} · Rated
Score55.1#280% interval48.5–61.74/4 Measured dimensionsMultimodal Grounded score79.2#14 / 56MMMU-Pro83.9#2 / 31
Multimodal
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Perception & OCR53
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
simplevqa · simple_vqa · z 0.43 · q 1.00
Document & spatial understanding47.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
charxiv · charxiv · z -0.15 · q 1.00
Visual reasoning64.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
erqa · erqa · z 0.61 · q 1.00
medxpert · med_xpert_qa_mm · z 0.86 · q 0.75
mmmu_pro · mmmu_pro · z 1.46 · q 1.00
Video & grounded action55.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
screenspot · screen_spot_pro · z 0.39 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score55.380% interval39.3–71.31/4 Measured dimensionsAA-IFBench77.1#7 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization55.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.41 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Pricing Comparison
Compare Gemini 3.1 Pro API pricing across 650 providers. Prices range from $0.0050/request to $1600.00/M. 小老鼠的奶酪工坊-酒馆聊天api offers the lowest rate at $0.0050/request. 15 providers offer free API credits or a free tier.
Showing 20 model IDs of 269.
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.
235 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.
216 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.
216 shared providers
Gemini 3 Flash
gemini-3-flash
Google Gemini 3 Flash is a next-generation fast multimodal model for responsive assistants, document understanding, and high-throughput API traffic.
215 shared providers
GPT-5.3 Codex
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
209 shared providers
GPT-5.2
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
204 shared providers
Frequently Asked Questions
- What benchmark data does Gemini 3.1 Pro include?
- LMSpeed shows Gemini 3.1 Pro benchmark context, API price, output speed, first-token latency, and provider data across 665 providers when those signals are available.
- What is the Gemini 3.1 Pro API price?
- Gemini 3.1 Pro has pricing from undefined provider} other undefined providers}}, ranging from $0.0050/request to $1600.00/M. 小老鼠的奶酪工坊-酒馆聊天api has the lowest listed price.
- What does the Gemini 3.1 Pro API pricing table include?
- The Gemini 3.1 Pro API pricing table compares 665 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 3.1 Pro API pricing?
- 小老鼠的奶酪工坊-酒馆聊天api currently has the lowest listed Gemini 3.1 Pro price at $0.0050/request across undefined provider} other undefined providers}}.
- Can I compare Gemini 3.1 Pro API price and speed together?
- Yes. LMSpeed shows Gemini 3.1 Pro API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Gemini 3.1 Pro API free?
- Yes, Gemini 3.1 Pro free API options are available through 15 providerundefined other undefined} on LMSpeed, including 兔子API, 梦德 API, 梦德 API, 兔子API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Gemini 3.1 Pro free API access?
- LMSpeed currently lists 15 free API providerundefined other undefined} for Gemini 3.1 Pro: 兔子API, 梦德 API, 梦德 API, 兔子API, 兔子API. Check each provider row before using it because free tier limits can change.