MoonshotAI
·Released on Jul 16, 2026Kimi K3 API Benchmarks, Pricing & Provider Data
Compare Kimi K3 with another model
Choose a model to open its comparison page.
LLM
Kimi K3 benchmark, API pricing, and provider data cover 147 API providers, with prices starting at $0.0030/request. Kimi K3 free API options are available from 5 providers. The page also shows measured API speed and first-token latency.
Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly stron...
Quality
#3of 110
80.0
LMSpeed score
Speed
#77of 80
154char/s
31.37 s
Cost
#158of 185
$0.0030/ 1M · 8:1 in:out
$0.0005 in · $0.0025 out
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 5 / 8
- Methodology
- V3.0
#1Agents65.8RatedGlobal rank #13/4 Measured dimensions
80% interval: 58.5–73.0
planningPrior only
tool use63.7
mcp_atlas · mcp_atlas / tau · aa_tau3_banking
environment execution68.4
browsecomp · browse_comp / deep_search_qa · deep_search_qa / enterprise_ops_gym · aa_enterprise_ops_gym / gdpval_aa · benchlm_agentic_gdpval_aa / itbench · aa_itbench / terminalbench · benchlm_agentic_terminal_bench2
recovery reliability65.2
apex_agents · apex_agents_aa / briefcase · aa_briefcase_elo / harvey_lab · aa_harvey_lab / jobbench · job_bench
#2Multimodal64.9Estimated2/4 Measured dimensions
80% interval: 53.6–76.2
perception ocrPrior only
document spatial60.9
charxiv · charxiv
visual reasoning68.9
mathvision · math_vision / mmmu_pro · mmmu_pro
video actionPrior only
#3Knowledge59.3Provisional1/4 Measured dimensions
80% interval: 45.3–73.3
broad knowledge59.3
aa_omniscience · aa_omniscience_index / benchlm_category_knowledge · benchlm_category_knowledge
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
#4Reasoning59Estimated2/4 Measured dimensions
80% interval: 48.2–69.8
abstract logicPrior only
scientific causal58
critpt · critpt / gpqa · gpqa / hle · hle / hle · hle_no_tools
multistep constraintsPrior only
evidence verification60
lcr · lcr
#5Coding55.8Estimated2/4 Measured dimensions
80% interval: 43.9–67.7
code generation57.3
scicode · scicode
repository engineeringPrior only
debugging testingPrior only
tooling quality54.3
terminalbench · aa_terminal_bench21
No data:MathMultilingualInstruction following
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
943.7Ktokens
8K128K1M4M
1.0M
Features
Technical Details
- Input
- Output
- Released
- Jul 2026
- Tokenizer
- Other
- Architecture
- text+image+video->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
It's decent at
Falls behind in
Detailed scores
Updated: Sep 5, 2026Overall
undefined metric} other undefined metrics}}
Overall score80.0#3 / 110DeepSWE67.5#7 / 21
Overall
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Speed & latency
undefined metric} other undefined metrics}}
Output speed37.9 tok/s#77 / 80Time to first token3.13 s#60 / 80
Speed & latency
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Time to first token
LMSpeed rank#60
Score3.13 s
Sourceartificialanalysis.ai
UpdatedSep 5, 2026
Confidence4
Pricing
undefined metric} other undefined metrics}}
Input price$3.00/M#158 / 185Output price$15.00/M#158 / 185
Pricing
undefined metric} other undefined metrics}}
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Score65.8#180% interval58.5–73.03/4 Measured dimensionsAgentic score91.0#2 / 76GDPval-AA1668.0#9 / 72
Agents
V3.0undefined metric} other undefined metrics}} · Rated
Dimensions and evidence
Planning & decompositionPrior only
Tool use63.7
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mcp_atlas · mcp_atlas · z 1.21 · q 1.00
tau · aa_tau3_banking · z 0.55 · q 1.00
Environment & long-horizon execution68.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
browsecomp · browse_comp · z 1.19 · q 1.00
deep_search_qa · deep_search_qa · z 1.20 · q 1.00
enterprise_ops_gym · aa_enterprise_ops_gym · z 0.16 · q 1.00
gdpval_aa · benchlm_agentic_gdpval_aa · z 1.16 · q 1.00
itbench · aa_itbench · z 0.70 · q 1.00
terminalbench · benchlm_agentic_terminal_bench2 · z 2.14 · q 1.00
Recovery & completion reliability65.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
apex_agents · apex_agents_aa · z 0.94 · q 1.00
briefcase · aa_briefcase_elo · z 0.41 · q 1.00
harvey_lab · aa_harvey_lab · z 1.07 · q 1.00
jobbench · job_bench · z 0.91 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score55.880% interval43.9–67.72/4 Measured dimensionsSciCode59.5%#2 / 37FrontierSWE81.2#1 / 2
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Code generation57.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
scicode · scicode · z 0.82 · q 1.00
Repository engineeringPrior only
Debugging & testingPrior only
Tool-assisted development & quality54.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
terminalbench · aa_terminal_bench21 · z 0.08 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
AA Terminal-Bench 2.1V3 evidence
LMSpeed rank#10
Score85.0
Sourcebenchlm.ai
UpdatedSep 5, 2026
Confidence3
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score5980% interval48.2–69.82/4 Measured dimensionsGPQA93.5%#7 / 217HLE46.9%#12 / 214
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning58
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z 0.87 · q 1.00
gpqa · gpqa · z 0.39 · q 1.00
hle · hle · z 0.45 · q 1.00
hle · hle_no_tools · z 0.09 · q 1.00
Multi-step constraintsPrior only
Evidence integration & verification60
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z 0.90 · q 1.00
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score59.380% interval45.3–73.31/4 Measured dimensionsKnowledge score82.1#11 / 82GPQA-D93.5#7 / 32
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Dimensions and evidence
Broad knowledge59.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z 0.78 · q 1.00
benchlm_category_knowledge · benchlm_category_knowledge · z 0.73 · 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#7
Score59.7
Sourcebenchlm.ai
UpdatedSep 5, 2026
Confidence3
AA-Omniscience IndexV3 evidence
LMSpeed rank#19
Score19.7
Sourcebenchlm.ai
UpdatedSep 5, 2026
Confidence3
AA-Omniscience Hallucination Rate
LMSpeed rank#72
Score53.2
Sourcebenchlm.ai
UpdatedSep 5, 2026
Confidence3
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
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
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
Score64.980% interval53.6–76.22/4 Measured dimensionsMultimodal Grounded score88.8#1 / 55OfficeQA Pro63.3#3 / 10
Multimodal
V3.0undefined metric} other undefined metrics}} · Estimated
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understanding60.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
charxiv · charxiv · z 1.60 · q 1.00
Visual reasoning68.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mathvision · math_vision · z 3.00 · q 1.00
mmmu_pro · mmmu_pro · z 0.80 · q 1.00
Video & grounded actionPrior only
Benchmark
LMSpeed rank
Score
Source
Updated
Confidence
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalizationPrior only
Multi-turn & long instructionsPrior only
OpenRouter endpoints
18 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 |
|---|---|---|---|---|---|---|
Modal modal/mxfp4 | $3/M | $15/M | 99.9% | — | — | undefined tokens / undefined tokens |
Sail Research sail-research/fp4 | $2.60/M | $13/M | 99.9% | — | — | undefined tokens / undefined tokens |
Wafer wafer | $3/M | $12.75/M | 99.9% | — | — | undefined tokens / undefined tokens |
DigitalOcean digitalocean | $2.85/M | $14.25/M | 99.9% | — | — | undefined tokens / undefined tokens |
Moonshot AI moonshotai/mxfp4 | $3/M | $15/M | 99.9% | — | — | undefined tokens / undefined tokens |
Fireworks fireworks | $3/M | $15/M | 99.8% | — | — | undefined tokens / undefined tokens |
Together together | $3/M | $15/M | 99.5% | — | — | undefined tokens / undefined tokens |
Chutes chutes/mxfp4 | $3/M | $15/M | 99.1% | — | — | undefined tokens / undefined tokens |
Morph morph/fp4 | $2.50/M | $14/M | 99.0% | — | — | undefined tokens / undefined tokens |
Fireworks fireworks/us | $3.30/M | $16.50/M | 98.8% | — | — | undefined tokens / undefined tokens |
Morph morph/fast | $6/M | $22.50/M | 98.7% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/bf16 | $2.85/M | $14.25/M | 98.6% | — | — | undefined tokens / undefined tokens |
Makora makora | $2.55/M | $12.75/M | 98.4% | — | — | undefined tokens / undefined tokens |
Phala phala | $3/M | $15/M | 95.3% | — | — | undefined tokens / undefined tokens |
BaseTen baseten/fp8 | $3/M | $15/M | 95.2% | — | — | undefined tokens / undefined tokens |
Alibaba alibaba | $3.45/M | $17.25/M | 93.0% | — | — | undefined tokens / undefined tokens |
Fireworks fireworks/fast | $4.50/M | $22.50/M | 92.1% | — | — | undefined tokens / undefined tokens |
Parasail parasail/fp4 | $3/M | $15/M | 91.5% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Kimi K3 API pricing across 142 providers. Prices range from $0.0030/request to $749250.00/M. Crond offers the lowest rate at $0.0030/request. 5 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 99% | kimi-k3 | kimi-sale | -38%$1.86/M Cache read$0.186/M | -38%$9.29/M | — | — | — | |
L1 100% | Kimi-K3 | default | $0.280/request | - | — | — | — | |
L1 100% | kimi-k3 | sale | $10.00/M | $50.00/M | — | — | — | |
L1 99% | kimi-k3 | Moonshot | -85%$0.441/M Cache read$0.044/M | -85%$2.20/M | — | — | — | |
L1 100% | kimi-k3 | default | -9%$2.74/M | -9%$13.70/M | — | — | — | |
L1 100% | kimi-k3 | 纯AZ | $4.11/M Cache read$0.411/M | $20.55/M | — | — | — | |
兔子API Free | L1 100% | kimi-k3 | 官方优惠 | Free | Free | — | — | — |
APIMart Free | L1 100% | kimi-k3 | default | Free | Free | — | — | — |
L1 100% | kimi-k3 | deepseek | -63%$1.10/M Cache read$0.110/M | -63%$5.48/M | — | — | — | |
L1 99% | kimi-k3 | default | -40%$1.80/M Cache read$0.180/M | -40%$9.00/M | — | — | — | |
L1 100% | kimi-k3 | Kimi-officially | -27%$2.19/M Cache read$0.219/M | -27%$10.96/M | — | — | — | |
L1 100% | kimi-k3 | deepseek-低价 | $20.00/M | $100.00/M | — | — | — | |
L1 100% L2 39% | kimi-k3 | default | $75.00/M | $75.00/M | — | — | — | |
L1 100% | 熊猫-按量-满血非量化-kimi-k3 | default | -99%$0.044/M Cache read$10.07/M | -99%$0.222/M | — | — | — | |
L1 100% | kimi-k3 | default | -65%$1.04/M | -65%$5.18/M | — | — | — | |
L1 99% | kimi-k3 | kimi | -63%$1.10/M Cache read$0.110/M | -63%$5.48/M | — | — | ||
L1 100% | kimi-k3 | default | -54%$1.37/M Cache read$0.137/M | -54%$6.85/M | — | — | — | |
L1 99% | kimi-k3 | Kimi | -9%$2.74/M Cache read$0.274/M | -9%$13.70/M | — | — | — | |
L1 100% | [mt]q|次/kimi-k3 | default | $27.00/request | - | — | — | — | |
L1 100% | [lq]q|SK/kimi-k3 | default | $30.00/request | - | — | — | — |
Showing 20 model IDs of 81.
Alternatives & Similar Models
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.
102 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.
101 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.
96 shared providers
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.
95 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.
94 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.
91 shared providers
Frequently Asked Questions
- What benchmark data does Kimi K3 include?
- LMSpeed shows Kimi K3 benchmark context, API price, output speed, first-token latency, and provider data across 147 providers when those signals are available.
- What is the Kimi K3 API price?
- Kimi K3 has pricing from 147 providers, ranging from $0.0030/request to $749250.00/M. Crond has the lowest listed price.
- What does the Kimi K3 API pricing table include?
- The Kimi K3 API pricing table compares 147 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Kimi K3 API pricing?
- Crond currently has the lowest listed Kimi K3 price at $0.0030/request across 147 providers.
- Can I compare Kimi K3 API price and speed together?
- Yes. LMSpeed shows Kimi K3 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Kimi K3 API free?
- Yes, Kimi K3 free API options are available through 5 providerundefined other undefined} on LMSpeed, including 兔子API, APIMart, Zero API, Dext API, 兔子API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Kimi K3 free API access?
- LMSpeed currently lists 5 free API providerundefined other undefined} for Kimi K3: 兔子API, APIMart, Zero API, Dext API, 兔子API. Check each provider row before using it because free tier limits can change.