impulse

Kimi K2 Thinking 251104

Open weights

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

API id kimi-k2-thinking-251104Released 6 Nov 2025 (Nov 2025)
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
229K
tokens
Max output
33K
tokens per reply
Hosts
1
1 listings
Released
Nov 2025
6 Nov 2025

Where to run it

1 host serve Kimi K2 Thinking 251104. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
kimi-k2-thinking-251104
-

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
Text
Produces
Text
Features
Assistant prefillPrompt caching
Open weights
License: Modified MIT License
Runs in about 2463.4 GB of GPU memory
Runtimes: SGLang, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Moonshot AI models

No similar Moonshot AI model keeps its key capabilities.

Other frontier labs

  • GPT-5.5 Pro
    OpenAI · on OpenAI
    $30.00 / $180.00
    Has every key capability
  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability

Call it

Using Volcengine's API.

Python
from litellm import completion

response = completion(
    model="volcengine/kimi-k2-thinking-251104",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer Kimi K2 Thinking 251104?

Kimi K2 Thinking 251104 runs on 1 API: Volcengine.

What is Kimi K2 Thinking 251104's context window?

229K tokens, with up to 33K tokens in one reply.

Is Kimi K2 Thinking 251104 being retired?

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

When was Kimi K2 Thinking 251104 released?

Moonshot AI released it on 6 Nov 2025.

What is Kimi K2 Thinking 251104's API model id?

Use kimi-k2-thinking-251104 with Volcengine.

Sources

Raw catalog entry for kimi-k2-thinking-251104 on Volcengine
{
  "input_cost_per_token": 0,
  "litellm_provider": "volcengine",
  "max_input_tokens": 229376,
  "max_output_tokens": 32768,
  "mode": "chat",
  "output_cost_per_token": 0,
  "supports_assistant_prefill": true,
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_tool_choice": true
}