impulse

Kimi K3.1 Pro

Open weights

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window.

API id kimi-k3.1-proReleased 23 Oct 2026 (4 weeks ago)
Input / 1M
$2.00
at Moonshot AI
Output / 1M
$10.00
at Moonshot AI
Context window
1M
tokens
Max output
1M
tokens per reply
Hosts
10
10 listings
Released
4 weeks ago
23 Oct 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$2.00$10.00
Cached input
90% off input
$0.20
Cache write, 5 minutes$2.00
Cache write, 1 hour$4.00

What it costs a month

At Moonshot AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,188
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$888
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,488
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$7,200
Use your own numbers

Where to run it

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

HostIn / out per 1M
kimi-k3.1-pro
$2.00 / $10.00
databricks-kimi-k3-1-pro
$2.00 / $10.00
kimi-k3-1-pro
$2.00 / $10.00
kimi-k3.1-pro
$2.00 / $10.00
BasetenInference
Kimi-K3.1-Pro
$2.00 / $10.00
Kimi-K3.1-Pro
$2.00 / $10.00
Together AIInference
Kimi-K3.1-Pro
$2.00 / $10.00
GMI CloudInference
kimi-k3.1-pro
$2.00 / $10.00
Fireworks AIInference
kimi-k3p1-pro
$2.00 / $10.00
kimi-k3.1-pro
$2.70 / $13.50
+35% 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
TextImages
Produces
Text
Effort settings the source lists
lowhighmax
Features
Prompt caching
Open weights
License: Modified MIT License
Runs in about 6672.3 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

No host sells it for less than Moonshot AI.

Smaller Moonshot AI models

No cheaper Moonshot AI model keeps its key capabilities.

Other frontier labs

  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    25% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    25% less
  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    50% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    95% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    47% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    57% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    83% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    87% less

Call it

Using Moonshot AI's API.

Python
from litellm import completion

response = completion(
    model="moonshot/kimi-k3.1-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Kimi K3.1 Pro cost?

On Moonshot AI, Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens. Cached input costs $0.20 per million tokens.

Which APIs offer Kimi K3.1 Pro?

Kimi K3.1 Pro runs on 10 APIs: Moonshot AI, Databricks, EmpirioLabs AI, OpenCode Go, Baseten, Nebius AI Studio, Together AI, GMI Cloud, Fireworks AI and Kyma API.

What is Kimi K3.1 Pro's context window?

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

Is Kimi K3.1 Pro being retired?

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

What are cheaper alternatives to Kimi K3.1 Pro?

Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (25% less), Grok 4.7 on xAI (25% less) and Qwen4 Max on Together AI (47% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Kimi K3.1 Pro released?

Moonshot AI released it on 23 Oct 2026.

What is Kimi K3.1 Pro's API model id?

Use kimi-k3.1-pro with Moonshot AI. Other hosts use their own ids: databricks-kimi-k3-1-pro on Databricks, kimi-k3-1-pro on EmpirioLabs AI, Kimi-K3.1-Pro on Baseten, Kimi-K3.1-Pro on Nebius AI Studio.

Sources

Raw catalog entry for kimi-k3.1-pro on Moonshot AI
{
  "cache_creation_input_token_cost": 0.000002,
  "cache_creation_input_token_cost_above_1hr": 0.000004,
  "cache_read_input_token_cost": 2e-7,
  "input_cost_per_token": 0.000002,
  "litellm_provider": "moonshot",
  "max_input_tokens": 1048576,
  "max_output_tokens": 1048576,
  "mode": "chat",
  "output_cost_per_token": 0.00001,
  "reasoning_effort_levels": [
    "low",
    "high",
    "max"
  ],
  "source": "https://platform.kimi.ai/docs/pricing/chat",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_vision": true
}