Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
kimi-k3Released 16 Jul 2026 (Jul 2026)Pricing
List prices at Moonshot AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $3.00 | $15.00 | |
| Cached input 90% off input | $0.30 | 90% off input | |
| 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
Where to run it
20 hosts serve Kimi K3. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Moonshot AILab API kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
SailCloud Kimi-K3 | $2.50 / $12.50 −17% vs headline | Kimi-K3 | |
ai&Cloud kimi-k3 | $3.00 / $12.50 −10% vs headline | kimi-k3 | |
SCX.aiCloud Kimi-K3 | $2.83 / $14.13 −6% vs headline | Kimi-K3 | |
DeepInfraInference Kimi-K3 | $2.85 / $14.25 −5% vs headline | Kimi-K3 | |
DatabricksCloud databricks-kimi-k3 | $3.00 / $15.00 | databricks-kimi-k3 | |
EmpirioLabs AICloud kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
OpenCode GoCloud kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
Tencent TokenHubCloud kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
WallyCloud kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
BasetenInference Kimi-K3 | $3.00 / $15.00 | Kimi-K3 | |
Nebius AI StudioInference Kimi-K3 | $3.00 / $15.00 | Kimi-K3 | |
Together AIInference Kimi-K3 | $3.00 / $15.00 | Kimi-K3 | |
Fireworks AIInference kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
GMI CloudInference kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
Novita AIInference kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
AIHubMixGateway kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
PerplexityGateway kimi-k3 | $3.00 / $15.00 | kimi-k3 | |
Kyma APICloud kimi-k3 | $3.05 / $15.26 +2% vs headline | kimi-k3 | |
Amazon BedrockCloud moonshotai.kimi-k3 | $3.30 / $16.50 +10% vs headline | moonshotai.kimi-k3 | |
GitHub CopilotSubscription kimi-k3 | In the subscription Retires 14 Dec 2026 | kimi-k3 | Retires 14 Dec 2026 |
Show 6 more listings: regions, snapshots and variantsHide regional listings
| Fireworks AI | |||||||
| Alias kimi-k3 | $3.00 / $15.00 | kimi-k3 | |||||
| Amazon Bedrock | |||||||
| global global.moonshotai.kimi-k3 | $3.00 / $15.00 | global.moonshotai.kimi-k3 | |||||
| in in.moonshotai.kimi-k3 | $3.30 / $16.50 +10% vs headline | in.moonshotai.kimi-k3 | |||||
| us us.moonshotai.kimi-k3 | $3.30 / $16.50 +10% vs headline | us.moonshotai.kimi-k3 | |||||
| us-gov-east-1 moonshotai.kimi-k3 | $3.96 / $19.80 +32% vs headline | moonshotai.kimi-k3 | |||||
| us-gov-west-1 moonshotai.kimi-k3 | $3.96 / $19.80 +32% vs headline | moonshotai.kimi-k3 | |||||
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 LicenseRuns in about 6671.8 GB of GPU memoryRuntimes: 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
- Sail17% lessKimi-K3$2.50 / $12.50
- ai&10% lesskimi-k3$3.00 / $12.50
- SCX.ai6% lessKimi-K3$2.83 / $14.13
- DeepInfra5% lessKimi-K3$2.85 / $14.25
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 20% less
- 33% less
- 33% less
- 50% less
Open-weight picks
- 33% less
- 64% less
- 71% less
- 91% less
Model line
Newer and older versions, at each lab's own price.
Call it
Using Moonshot AI's API.
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
- Baseten pricing
- DeepInfra pricing
- Nebius AI Studio pricing
- Sail pricing
- SCX.ai pricing
- Together AI pricing
- Databricks pricing
- Amazon Bedrock pricing
- ai& pricing
- AIHubMix pricing
- EmpirioLabs AI pricing
- Fireworks AI pricing
- GitHub Copilot pricing
- GMI Cloud pricing
- Moonshot AI pricing
- Novita AI pricing
- OpenCode Go pricing
- Perplexity pricing
- Tencent TokenHub pricing
- Wally pricing
- LiteLLM model map
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
}