MoonshotAI: Kimi K3

moonshotai/kimi-k3

Last Observed: 2026-10-15 06:03:56.513884 UTC

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Find A Field

Architecture And Modalities · 3

Architecture · Instruct Type API Details /architecture/instruct_type Explicit Null	Explicit Null
Architecture · Modality API Details /architecture/modality text+image+video->text	text+image+video->text
Architecture · Tokenizer API Details /architecture/tokenizer Other	Other

Benchmarks · 3

Benchmarks · Artificial Analysis · Agentic Index API Details /benchmarks/artificial_analysis/agentic_index 50	50
Benchmarks · Artificial Analysis · Coding Index API Details /benchmarks/artificial_analysis/coding_index 76.2	76.2
Benchmarks · Artificial Analysis · Intelligence Index API Details /benchmarks/artificial_analysis/intelligence_index 43.6	43.6

Catalog Identity And Metadata · 11

Canonical Slug API Details /canonical_slug moonshotai/kimi-k3-20260715	moonshotai/kimi-k3-20260715
Context Tokens API Details /context_length 1048576	1,048,576
Created API Details /created 1784215858	2026-07-16 15:30:58 UTC
Description API Details /description Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...	Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Expiration Date API Details /expiration_date Explicit Null	Explicit Null
Hugging Face Id API Details /hugging_face_id moonshotai/Kimi-K3	moonshotai/Kimi-K3
Id API Details /id moonshotai/kimi-k3	moonshotai/kimi-k3
Knowledge Cutoff API Details /knowledge_cutoff Explicit Null	Explicit Null
Links · Details API Details /links/details /api/v1/models/moonshotai/kimi-k3-20260715/endpoints	/api/v1/models/moonshotai/kimi-k3-20260715/endpoints
Name API Details /name MoonshotAI: Kimi K3	MoonshotAI: Kimi K3
Supported Voices API Details /supported_voices Explicit Null	Explicit Null

Default Parameters · 6

Default Parameters · Frequency Penalty API Details /default_parameters/frequency_penalty Explicit Null	Explicit Null
Default Parameters · Presence Penalty API Details /default_parameters/presence_penalty Explicit Null	Explicit Null
Default Parameters · Repetition Penalty API Details /default_parameters/repetition_penalty Explicit Null	Explicit Null
Default Parameters · Temperature API Details /default_parameters/temperature Explicit Null	Explicit Null
Default Parameters · Top K API Details /default_parameters/top_k Explicit Null	Explicit Null
Default Parameters · Top P API Details /default_parameters/top_p 0.95	0.95

Request Limits · 1

Per Request Limits API Details /per_request_limits Explicit Null	Explicit Null

Pricing · 3

Output Price · USD/Token API Details /pricing/completion 0.000015	0.000015
Pricing · Input Cache Read API Details /pricing/input_cache_read 0.00000028	0.00000028
Input Price · USD/Token API Details /pricing/prompt 0.00000045	0.00000045

Reasoning · 3

Reasoning · Default Effort API Details /reasoning/default_effort max	max
Reasoning · Default Enabled API Details /reasoning/default_enabled True	True
Reasoning · Mandatory API Details /reasoning/mandatory False	False

Provider Limits · 3

Top Provider · Context Length API Details /top_provider/context_length 1048576	1,048,576
Top Provider · Is Moderated API Details /top_provider/is_moderated False	False
Top Provider · Max Completion Tokens API Details /top_provider/max_completion_tokens 943718	943,718

API Structure And Container Types

Architecture API Details /architecture Object · See Fields	Object · See Fields
Architecture · Input Modalities API Details /architecture/input_modalities Array · See Items	Array · See Items
Architecture · Output Modalities API Details /architecture/output_modalities Array · See Items	Array · See Items
Benchmarks API Details /benchmarks Object · See Fields	Object · See Fields
Benchmarks · Artificial Analysis API Details /benchmarks/artificial_analysis Object · See Fields	Object · See Fields
Benchmarks · Design Arena API Details /benchmarks/design_arena Array · See Items	Array · See Items
Default Parameters API Details /default_parameters Object · See Fields	Object · See Fields
Links API Details /links Object · See Fields	Object · See Fields
Pricing API Details /pricing Object · See Fields	Object · See Fields
Reasoning API Details /reasoning Object · See Fields	Object · See Fields
Reasoning · Supported Efforts API Details /reasoning/supported_efforts Array · See Items	Array · See Items
Supported Parameters API Details /supported_parameters Array · See Items	Array · See Items
Top Provider API Details /top_provider Object · See Fields	Object · See Fields

Architecture · Input Modalities

3 items · source order preserved

text
image
video

API Details

Item	/architecture/input_modalities/*
1	text
2	image
3	video

Architecture · Output Modalities

1 items · source order preserved

text

API Details

Item	/architecture/output_modalities/*
1	text

Supported Parameters

20 items · source order preserved

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

API Details

Item	/supported_parameters/*
1	frequency_penalty
2	include_reasoning
3	logit_bias
4	logprobs
5	max_tokens
6	min_p
7	presence_penalty
8	reasoning
9	reasoning_effort
10	repetition_penalty
11	response_format
12	seed
13	stop
14	structured_outputs
15	temperature
16	tool_choice
17	tools
18	top_k
19	top_logprobs
20	top_p

Benchmarks · Design Arena

15 items · source order preserved

Item	Arena	Category	Elo	Rank	Win Rate
1	agents	agenticgamedev	1252	3	55
2	agents	androidnative	1262	5	55.4
3	agents	fullstack	1315	2	61.8
4	agents	godotgamedev	1223	14	48.2
5	agents	htmlslides	1256	2	59.6
6	agents	mobileapps	1264	4	57
7	agents	python-pptxslides	1273	4	59.2
8	agents	webapps	1285	4	59
9	models	3d	1389	7	67.3
10	models	codecategories	1363	4	62.4
11	models	dataviz	1352	4	63.2
12	models	gamedev	1364	7	60.9
13	models	svg	1299	6	59.2
14	models	uicomponent	1346	6	60.3
15	models	website	1336	4	59.2

API Details

Item	/benchmarks/design_arena/*/arena	/benchmarks/design_arena/*/category	/benchmarks/design_arena/*/elo	/benchmarks/design_arena/*/rank	/benchmarks/design_arena/*/win_rate
1	agents	agenticgamedev	1252	3	55
2	agents	androidnative	1262	5	55.4
3	agents	fullstack	1315	2	61.8
4	agents	godotgamedev	1223	14	48.2
5	agents	htmlslides	1256	2	59.6
6	agents	mobileapps	1264	4	57
7	agents	python-pptxslides	1273	4	59.2
8	agents	webapps	1285	4	59
9	models	3d	1389	7	67.3
10	models	codecategories	1363	4	62.4
11	models	dataviz	1352	4	63.2
12	models	gamedev	1364	7	60.9
13	models	svg	1299	6	59.2
14	models	uicomponent	1346	6	60.3
15	models	website	1336	4	59.2

Reasoning · Supported Efforts

3 items · source order preserved

max
high
low

API Details

Item	/reasoning/supported_efforts/*
1	max
2	high
3	low

Recorded Value History

Historical API Field

Input Price · USD/Token

7 of 7 records plotted · 0 excluded for missing or invalid coordinates.

Up to 100 recorded versions, spaced by observation order rather than elapsed time. Array fields use the minimum numeric item in each version. Missing values are omitted. Select a point to open its archived snapshot; comparison actions use the current listing. History begins at the first recorded baseline.

Axis Scale

Select a point to open its listing or add it to compare.

Browse The Full Table