impulse

Kimi K3

Open weights

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

API id kimi-k3Released 16 Jul 2026 (Jul 2026)
Input / 1M
$3.00
at Moonshot AI
Output / 1M
$15.00
at Moonshot AI
Context window
1M
tokens
Max output
1M
tokens per reply
Hosts
20
27 listings
Released
Jul 2026
16 Jul 2026

Pricing

List prices at Moonshot AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$3.00$15.00
Cached input
90% off input
$0.30
Cache write, 5 minutes$3.00
Cache write, 1 hour$6.00

What it costs a month

At Moonshot AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,782
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,332
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,232
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$10,800
Use your own numbers

Where to run it

20 hosts serve Kimi K3. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
kimi-k3
$3.00 / $15.00
SailCloud
Kimi-K3
$2.50 / $12.50
−17% vs headline
ai&Cloud
kimi-k3
$3.00 / $12.50
−10% vs headline
SCX.aiCloud
Kimi-K3
$2.83 / $14.13
−6% vs headline
DeepInfraInference
Kimi-K3
$2.85 / $14.25
−5% vs headline
databricks-kimi-k3
$3.00 / $15.00
kimi-k3
$3.00 / $15.00
kimi-k3
$3.00 / $15.00
kimi-k3
$3.00 / $15.00
WallyCloud
kimi-k3
$3.00 / $15.00
BasetenInference
Kimi-K3
$3.00 / $15.00
Kimi-K3
$3.00 / $15.00
Together AIInference
Kimi-K3
$3.00 / $15.00
Fireworks AIInference
kimi-k3
$3.00 / $15.00
GMI CloudInference
kimi-k3
$3.00 / $15.00
Novita AIInference
kimi-k3
$3.00 / $15.00
AIHubMixGateway
kimi-k3
$3.00 / $15.00
PerplexityGateway
kimi-k3
$3.00 / $15.00
kimi-k3
$3.05 / $15.26
+2% vs headline
moonshotai.kimi-k3
$3.30 / $16.50
+10% vs headline
GitHub CopilotSubscription
kimi-k3
In the subscription
Retires 14 Dec 2026
Show 6 more listings: regions, snapshots and variants
Fireworks AI
Alias
kimi-k3
$3.00 / $15.00
Amazon Bedrock
global
global.moonshotai.kimi-k3
$3.00 / $15.00
in
in.moonshotai.kimi-k3
$3.30 / $16.50
+10% vs headline
us
us.moonshotai.kimi-k3
$3.30 / $16.50
+10% vs headline
us-gov-east-1
moonshotai.kimi-k3
$3.96 / $19.80
+32% vs headline
us-gov-west-1
moonshotai.kimi-k3
$3.96 / $19.80
+32% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImagesVideo
Produces
Text
Effort settings the source lists
lowhighmax
Features
Prompt cachingVideo input
Open weights
License: Modified MIT License
Runs in about 6671.8 GB of GPU memory
Runtimes: SGLang, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • Sail
    Kimi-K3
    $2.50 / $12.50
    17% less
  • ai&
    kimi-k3
    $3.00 / $12.50
    10% less
  • SCX.ai
    Kimi-K3
    $2.83 / $14.13
    6% less
  • DeepInfra
    Kimi-K3
    $2.85 / $14.25
    5% less

Smaller Moonshot AI models

No cheaper Moonshot AI model keeps its key capabilities.

Other frontier labs

  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    20% less
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    33% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    33% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    50% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    33% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    64% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    71% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    91% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedKimi K3.1Latest$4.40 / $22.00
  2. Jul 2026Kimi K3This page$3.00 / $15.00
  3. UndatedKimi K2.7$0.95 / $4.00
  4. Apr 2026Kimi K2.6$0.95 / $4.00
  5. Jan 2026Kimi K2.5$0.60 / $3.00
  6. Jul 2025Kimi K2$0.55 / $2.20

Call it

Using Moonshot AI's API.

Python
from litellm import completion

response = completion(
    model="moonshot/kimi-k3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Kimi K3 cost?

On Moonshot AI, Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens. Cached input costs $0.30 per million tokens. The cheapest host is Sail, at $2.50 per million input tokens and $12.50 per million output tokens.

Which APIs offer Kimi K3?

Kimi K3 runs on 20 APIs: Moonshot AI, Sail, ai&, SCX.ai, DeepInfra, Databricks, EmpirioLabs AI, OpenCode Go, Tencent TokenHub and 11 more.

What is Kimi K3's context window?

1M tokens, with up to 1M tokens in one reply.

Is Kimi K3 being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Kimi K3?

Yes. Kimi K3.1 is the newest model in this line.

What are cheaper alternatives to Kimi K3?

Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (20% less), Gemini 4 Carbon on Google AI Studio (33% less) and Kimi K3.1 Pro on Databricks (33% less). Kimi K3 itself costs 17% less on Sail. Savings are on a mix of 3 input tokens to 1 output token.

When was Kimi K3 released?

Moonshot AI released it on 16 Jul 2026.

What is Kimi K3's API model id?

Use kimi-k3 with Moonshot AI. Other hosts use their own ids: Kimi-K3 on Sail, Kimi-K3 on SCX.ai, Kimi-K3 on DeepInfra, databricks-kimi-k3 on Databricks.

Sources

Raw catalog entry for kimi-k3 on Moonshot AI
{
  "cache_creation_input_token_cost": 0.000003,
  "cache_creation_input_token_cost_above_1hr": 0.000006,
  "cache_read_input_token_cost": 3e-7,
  "input_cost_per_token": 0.000003,
  "litellm_provider": "moonshot",
  "max_input_tokens": 1048576,
  "max_output_tokens": 1048576,
  "mode": "chat",
  "output_cost_per_token": 0.000015,
  "reasoning_effort_levels": [
    "low",
    "high",
    "max"
  ],
  "source": "https://platform.kimi.ai/docs/pricing/chat-k3",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_video_input": true,
  "supports_vision": true
}