kimi-k3.1-pro API

kimi-k3.1-pro

kimi-k3.1-pro is available through APINEED. Compare current prices and use the request examples on this page to get started.

Use the backend model ID kimi-k3.1-pro when sending requests. Availability and performance are shown only when the public metrics APIs return recent data.

MODALITIES

CONTEXTN/A

curl 'https://apineed.com/v1/messages' \
  -H "x-api-key: $API_NEED_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
  "max_tokens": 1024,
  "messages": [
    {
      "content": "Hello",
      "role": "user"
    }
  ],
  "model": "kimi-k3.1-pro",
  "stream": false
}'

Playground

Try this text model for free. No sign-in required.

Open Playground

Chat with kimi-k3.1-pro model

APINEED pricing

Pay as you go. Current selling prices in USD.

Get API Key

Input

$2.34

APINEED rate/ 1M tokens

Output

$12.24

APINEED rate/ 1M tokens

Cache read

$0.24

APINEED rate/ 1M tokens

Benchmarks

Editorial benchmark data is shown when this model has a verified match.Intelligence uses the source’s median-score ranking. Efficiency views are APINEED calculations, not official LLM2014 rankings. Test costs and reference prices are converted at ¥7 per US dollar; they are not APINEED selling prices. Missing values are N/A. These results describe the source’s tested configurations, not guaranteed APINEED endpoint performance.


1st	GPT-5.5 (xhigh)	80.23	73.89	7.9%	534s	33,219	$27.51	$29.57
2nd	GPT-5.6 Sol (xhigh)	78.37	69.42	11.42%	381s	17,769	$14.71	$29.57
3rd	Kimi-K3 (max)	75.77	67.66	10.7%	1144s	41,432	$17.40	$15.00
4th	Claude Opus 5 (xhigh)	71.24	64.74	9.12%	437s	26,705	$18.43	$24.64
5th	GLM-5.3 (max)	74.48	63.91	14.19%	1009s	57,408	$6.43	$4.00
6th	GLM-5.3-Flash (max)	69.55	60.52	12.98%	863s	38,787	$0.22	$0.20
7th	Qwen3.8-Max (xhigh)	64.68	60.05	7.16%	1297s	65,135	$9.38	$5.14
8th	DeepSeek V4 Pro 0813(max)	70.13	59.63	14.97%	1601s	73,350	$7.92	$3.86
9th	DeepSeek-V4-Flash-Vision-Exp (max)	62.86	58.10	7.57%	974s	79,420	$2.86	$1.29
10th	Gemini 3.7 Flash (high)	66.62	57.56	13.6%	131s	26,596	$2.75	$3.70
11th	Grok 4.6 (high)	67.93	56.41	16.96%	813s	33,807	$5.60	$5.91
12th	Gemini 3.1 Pro (high)	69.35	55.84	19.48%	235s	28,338	$9.39	$11.83
13th	DeepSeek V4 Flash 0731 (max)	66.34	55.23	16.75%	881s	74,657	$2.69	$1.29
14th	GLM-5.2 (max)	66.53	54.70	17.78%	891s	46,273	$5.18	$4.00
15th	Qwen3.8-Flash (xhigh)	65.44	54.49	16.73%	844s	64,942	$0.70	$0.39
16th	GPT-5.6 Luna (xhigh)	65.92	51.62	21.69%	247s	37,885	$1.25	$1.18
17th	Qwen3.8-27B (xhigh)	58.48	47.65	18.52%	2318s	73,987	$3.55	$1.71
18th	Doubao-Seed-2.1-pro (high)	55.12	45.78	16.94%	2026s	85,238	$10.23	$4.29
19th	Muse Spark 1.2 (xhigh)	57.93	45.14	22.08%	359s	47,209	$5.54	$4.19
20th	Gemini 3.7 Flash (low)	53.50	44.06	17.64%	59s	10,673	$1.10	$3.70
21st	Claude Sonnet 5 (xhigh)	47.80	39.57	17.22%	545s	45,066	$12.44	$9.86
22nd	Tencent Hy3 (high)	57.89	39.51	31.75%	1076s	53,214	$0.85	$0.57
23rd	Qwen3.7-Plus (high)	51.36	38.74	24.57%	1254s	58,610	$1.88	$1.14
24th	MiniMax-M3	43.83	37.37	14.74%	982s	57,486	$1.93	$1.20
25th	Doubao-Seed-2.0-lite 0428 (high)	34.13	26.18	23.29%	669s	27,845	$0.40	$0.51
26th	Claude Opus 5	34.94	24.58	29.65%	156s	10,261	$7.08	$24.64
27th	Gemini 3.5 Flash Lite (high)	29.51	20.44	30.74%	192s	17,842	$1.23	$2.46
28th	Ling-3.0-flash	28.37	17.05	39.9%	735s	95,538	N/A	N/A
29th	Gemma 4 31B	21.36	16.09	24.67%	756s	15,290	$0.17	$0.39
30th	openPangu-2.0-Pro	20.02	15.75	21.33%	645s	28,215	$1.64	$2.07
31st	Qwen3.7-Plus	20.84	15.63	25%	323s	8,910	$0.29	$1.14
32nd	GPT-5.5 Instant	21.73	14.09	35.16%	28s	1,712	$1.42	$29.57
33rd	Mistral Medium 3.5	17.25	13.87	19.59%	200s	28,129	$5.82	$7.39
34th	Step-3.7-Flash	26.18	13.74	47.52%	282s	47,180	$1.53	$1.16
35th	MiMo-V2.5-Pro	26.31	13.00	50.59%	550s	33,095	$0.79	$0.86
36th	Dots3-Note Preview	18.63	12.95	30.49%	210s	28,386	N/A	N/A
37th	ERNIE 5.1	16.32	11.32	30.64%	468s	24,522	$1.77	$2.57
38th	Qwen3.8-27B	16.48	10.61	35.62%	192s	8,914	$0.43	$1.71
39th	openPangu-2.0-Flash	19.24	10.16	47.19%	583s	29,052	$0.19	$0.23
40th	LongCat-2.0	17.61	9.74	44.69%	374s	14,273	$0.46	$1.14
41st	Claude Sonnet 5	16.49	9.67	41.36%	113s	6,175	$1.70	$9.86
42nd	GLM-5.2	12.42	8.05	35.19%	24s	929	$0.10	$4.00
43rd	DeepSeek V4 Flash 0731	13.57	7.93	41.56%	53s	4,621	$0.17	$1.29
44th	Gemini 3.1 Flash Lite	9.01	7.11	21.09%	11s	707	$0.03	$1.48
45th	Doubao-Seed-2.1-pro	13.03	6.17	52.65%	319s	6,948	$0.83	$4.29
46th	Mistral Medium 3.5	8.45	5.93	29.82%	18s	2,589	$0.54	$7.39

Quick Start

Use /v1/messages with non-streaming output.

Create an API key

Store your APINEED API key in the API_NEED_API_KEY environment variable.

Send the request

curl 'https://apineed.com/v1/messages' \
  -H "x-api-key: $API_NEED_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'anthropic-version: 2023-06-01' \
  -d '{
  "max_tokens": 1024,
  "messages": [
    {
      "content": "Hello",
      "role": "user"
    }
  ],
  "model": "kimi-k3.1-pro",
  "stream": false
}'

Read the response

Read the completed JSON response and check errors before using the output.

const response = await fetch("https://apineed.com/v1/messages", {
  method: 'POST',
  headers: {
    "x-api-key": "" + (process.env.API_NEED_API_KEY ?? ''),
    "Content-Type": "application/json",
    "anthropic-version": "2023-06-01",
  },
  body: JSON.stringify({
  "max_tokens": 1024,
  "messages": [
    {
      "content": "Hello",
      "role": "user"
    }
  ],
  "model": "kimi-k3.1-pro",
  "stream": false
}),
})

if (!response.ok) throw new Error(await response.text())
console.log(await response.json())

Endpoints

Endpoints currently returned by the live pricing API.

POST/v1/messagesNon-streaming

x-api-key: API_NEED_API_KEY
Content-Type: application/json
anthropic-version: 2023-06-01
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

POST/v1/messagesStreaming

x-api-key: API_NEED_API_KEY
Content-Type: application/json
anthropic-version: 2023-06-01
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

POST/v1beta/models/kimi-k3.1-pro:generateContentNon-streaming

x-goog-api-key: API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model in URL: kimi-k3.1-pro

POST/v1beta/models/kimi-k3.1-pro:streamGenerateContent?alt=sseStreaming

x-goog-api-key: API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model in URL: kimi-k3.1-pro

POST/v1/chat/completionsNon-streaming

Authorization: Bearer API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

POST/v1/chat/completionsStreaming

Authorization: Bearer API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

POST/v1/responsesNon-streaming

Authorization: Bearer API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

POST/v1/responsesStreaming

Authorization: Bearer API_NEED_API_KEY
Content-Type: application/json
HTTP-Referer: optional - your site URL, for rankings
X-Title: optional - your site name, for rankings
Model: kimi-k3.1-pro

Parameters

Supported parameters are shown when verified metadata is available.

Name	Type	Status	Description
`model`	string	Required	Use kimi-k3.1-pro.
`messages`	array	Required	Conversation messages sent to the model.
`max_tokens`	integer	Required	Maximum output tokens.

Q&A

Common questions about the kimi-k3.1-pro API.

Which model ID should I use for kimi-k3.1-pro?

Use kimi-k3.1-pro, exactly as returned by the API Need pricing API.

Which endpoint should I use?

Send a POST request to /v1/messages using your APINEED API key. Follow the request example and parameter table on this page.

How is the API Need price calculated?

See Pricing for the current rates and discounts. Final charges use recorded usage.

How to deploy kimi-k3.1-pro

Connect the live model to your application.

Top up

Add usage credit in the product app.

Create a key

Create and securely store an API key.

Configure the endpoint

Send requests to /v1/messages.

Monitor responses

Track status, latency, and errors in your application.

More live models

kimi-k3moonshotai/kimi-k3