MiniMax
·Released on May 31, 2026MiniMax M3 API Benchmarks, Pricing & Provider Data
Compare MiniMax M3 with another model
Choose a model to open its comparison page.
LLM
MiniMax M3 benchmark, API pricing, and provider data cover 162 API providers, with prices starting at $0.0020/request. MiniMax M3 free API options are available from 5 providers. The page also shows measured API speed and first-token latency.
MiniMax M3 is MiniMax next-generation large language model, designed for advanced reasoning, long-context understanding, and high-quality multilingual dialogue.
Quality
#47of 100
57.0
LMSpeed score
Speed
#29of 77
81char/s
2.49 s
Cost
#55of 181
$0.0020/ 1M · 8:1 in:out
$0.0003 in · $0.0017 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Reasoning59.2Estimated2/4 Measured dimensions
80% interval: 48.4–70.0
abstract logicPrior only
scientific causal60.1
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraintsPrior only
evidence verification58.3
lcr · lcr
#2Instruction following57.8Provisional1/4 Measured dimensions
80% interval: 41.8–73.8
constraint followingPrior only
structured outputPrior only
novel instruction generalization57.8
ifbench · aa_if_bench
long multiturn instructionPrior only
#3Agents53.7RatedGlobal rank #243/4 Measured dimensions
80% interval: 46.3–61.0
planningPrior only
tool use47.7
mcp_atlas · mcp_atlas / tau · aa_tau3_banking / tau · tau2_bench
environment execution51.3
browsecomp · browse_comp / enterprise_ops_gym · aa_enterprise_ops_gym / gdpval_aa · benchlm_agentic_gdpval_aa / osworld · os_world2 / osworld · os_world_verified / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability62
briefcase · aa_briefcase_elo / claw_eval · claw_eval / harvey_lab · aa_harvey_lab / researchclaw · research_claw_bench
#4Coding52.7RatedGlobal rank #224/4 Measured dimensions
80% interval: 46.1–59.3
code generation56.1
scicode · scicode
repository engineering49.9
nl2repo · nl2_repo / swe_pro · swe_pro
debugging testing56.2
swe_verified · swe_verified
tooling quality48.5
terminalbench · aa_terminal_bench21 / terminalbench · benchlm_coding_terminal_bench2 / terminalbench · terminal_bench_hard
#5Knowledge51.7Provisional1/4 Measured dimensions
80% interval: 37.7–65.7
broad knowledge51.7
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#6Multimodal46.9Estimated2/4 Measured dimensions
80% interval: 34.9–58.9
perception ocrPrior only
document spatialPrior only
visual reasoning49.8
mmmu_pro · mmmu_pro
video action44.1
video_mmmu · video_mmmu
No data:MathMultilingual
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
512Ktokens
8K128K1M4M
1.0M
Features
Technical Details
- Input
- Output
- Released
- May 2026
- Tokenizer
- Other
- Architecture
- text+image+video->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 1, 2026Overall
undefined metric} other undefined metrics}}
Overall score57.0#47 / 100
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Speed & latency
undefined metric} other undefined metrics}}
Output speed125.9 tok/s#29 / 77Time to first token0.98 s#28 / 77
Speed & latency
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Time to first token
LMSpeed rank#28
Score0.98 s
Sourceartificialanalysis.ai
UpdatedSep 1, 2026
Confidence4
Pricing
undefined metric} other undefined metrics}}
Input price$0.300/M#55 / 181Output price$1.20/M#50 / 181
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score53.7#2480% interval46.3–61.03/4 Measured dimensionsAgentic score63.3#34 / 69Terminal-Bench 2.066.0#22 / 53
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decompositionPrior only
Tool use47.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z 0.09 · q 1.00
tau · aa_tau3_banking · z -2.94 · q 1.00
tau · tau2_bench · z 0.14 · q 1.00
Environment & long-horizon execution51.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
browsecomp · browse_comp · z 0.29 · q 1.00
enterprise_ops_gym · aa_enterprise_ops_gym · z -1.64 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z 0.53 · q 1.00
osworld · os_world2 · z -1.02 · q 1.00
osworld · os_world_verified · z -0.27 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 0.14 · q 1.00
Recovery & completion reliability62
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
briefcase · aa_briefcase_elo · z -0.37 · q 1.00
claw_eval · claw_eval · z 2.68 · q 1.00
harvey_lab · aa_harvey_lab · z -0.47 · q 1.00
researchclaw · research_claw_bench · z 0.54 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
AA EnterpriseOps-GymV3 evidence
LMSpeed rank#16
Score32.1
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence2
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Score52.7#2280% interval46.1–59.34/4 Measured dimensionsSciCode45.4%#48 / 206Coding score53.8#38 / 81
Coding
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Code generation56.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · scicode · z 0.69 · q 1.00
Repository engineering49.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
nl2repo · nl2_repo · z -0.13 · q 1.00
swe_pro · swe_pro · z 0.41 · q 1.00
Debugging & testing56.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
swe_verified · swe_verified · z 0.78 · q 1.00
Tool-assisted development & quality48.5
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
terminalbench · aa_terminal_bench21 · z -0.88 · q 1.00
terminalbench · benchlm_coding_terminal_bench2 · z -0.11 · q 1.00
terminalbench · terminal_bench_hard · z -0.04 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
AA Terminal-Bench 2.1V3 evidence
LMSpeed rank#13
Score65.2
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence2
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score59.280% interval48.4–70.02/4 Measured dimensionsGPQA92.9%#10 / 213HLE39.0%#29 / 210
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning60.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.12 · q 1.00
gpqa · gpqa · z 1.31 · q 1.00
hle · hle · z 0.91 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification58.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.76 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score51.780% interval37.7–65.71/4 Measured dimensionsArtificial Analysis Intelligence Index45.4#26 / 111AA-GPQA Diamond92.9#9 / 108
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge51.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 0.18 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z -0.17 · 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#26
Score45.4
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence2
AA-Omniscience Hallucination Rate
LMSpeed rank#100
Score18.4
Sourcebenchlm.ai
UpdatedSep 1, 2026
Confidence2
Math
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsUSAMO 202685.7#2 / 2
Math
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Foundational mathPrior only
Competition mathPrior only
Advanced proofsPrior only
Applied & tool-assisted mathPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
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
Score46.980% interval34.9–58.92/4 Measured dimensionsMultimodal Grounded score42.2#37 / 44OfficeQA Pro45.1#8 / 9
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoning49.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmmu_pro · mmmu_pro · z -0.10 · q 1.00
Video & grounded action44.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
video_mmmu · video_mmmu · z -0.03 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score57.880% interval41.8–73.81/4 Measured dimensionsAA-IFBench82.9#1 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization57.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z 0.76 · q 1.00
Multi-turn & long instructionsPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
OpenRouter endpoints
11 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 |
|---|---|---|---|---|---|---|
Venice venice/fp8 | $0.300/M | $1.20/M | 100.0% | — | — | undefined tokens / undefined tokens |
AtlasCloud atlas-cloud/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | undefined tokens / undefined tokens |
Novita novita/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | undefined tokens / undefined tokens |
Minimax minimax/fp8 | $0.300/M | $1.20/M | 99.8% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp8 | $0.280/M | $1.10/M | 99.7% | — | — | undefined tokens / undefined tokens |
Parasail parasail/fp8 | $0.300/M | $1.20/M | 99.6% | — | — | undefined tokens / undefined tokens |
StreamLake streamlake/fp8 | $0.300/M | $1.20/M | 99.5% | — | — | undefined tokens / undefined tokens |
ModelRun modelrun/fp4 | $0.750/M | $3/M | 99.1% | — | — | undefined tokens / undefined tokens |
CoreWeave coreweave/fp4 | $0.230/M | $0.960/M | 98.3% | — | — | undefined tokens / undefined tokens |
SambaNova sambanova | $0.600/M | $2.40/M | 98.0% | — | — | undefined tokens / undefined tokens |
GMICloud gmicloud/fp8 | $0.600/M | $2.40/M | 82.3% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare MiniMax M3 API pricing across 157 providers. Prices range from $0.0020/request to $2997.00/M. 3173721 API offers the lowest rate at $0.0020/request. 5 providers offer free API credits or a free tier.
Showing 20 model IDs of 82.
Alternatives & Similar Models
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.
113 shared providers
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
111 shared providers
GLM-5.2
glm-5-2
Zhipu GLM-5.2 is Zhipu latest flagship coding and agentic model with a 1M-token context window, enhanced reasoning modes, and long-horizon software engineering capabilities.
110 shared providers
GLM-5.1
glm-5-1
Zhipu GLM-5.1 is a next-generation GLM model aimed at frontier reasoning, coding, and bilingual agent applications.
105 shared providers
MiniMax M2.7
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
105 shared providers
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
101 shared providers
Frequently Asked Questions
- What benchmark data does MiniMax M3 include?
- LMSpeed shows MiniMax M3 benchmark context, API price, output speed, first-token latency, and provider data across 162 providers when those signals are available.
- What is the MiniMax M3 API price?
- MiniMax M3 has pricing from 162 providers, ranging from $0.0020/request to $2997.00/M. 3173721 API has the lowest listed price.
- What does the MiniMax M3 API pricing table include?
- The MiniMax M3 API pricing table compares 162 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest MiniMax M3 API pricing?
- 3173721 API currently has the lowest listed MiniMax M3 price at $0.0020/request across 162 providers.
- Can I compare MiniMax M3 API price and speed together?
- Yes. LMSpeed shows MiniMax M3 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is MiniMax M3 API free?
- Yes, MiniMax M3 free API options are available through 5 providerundefined other undefined} on LMSpeed, including 初叶🍂Furry API, Zero API, Moyanjdc API, Dext API, Dext API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get MiniMax M3 free API access?
- LMSpeed currently lists 5 free API providerundefined other undefined} for MiniMax M3: 初叶🍂Furry API, Zero API, Moyanjdc API, Dext API, Dext API. Check each provider row before using it because free tier limits can change.