Kimi K2.8 Preview
kimi-k2.8-previewPricing
List prices at Tencent TokenHub, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.00 | $4.00 | |
| Cached input 75% off input | $0.25 | 75% off input | |
| Cache write, 5 minutes | $0.00 |
What it costs a month
At Tencent TokenHub list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$533
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$444
- Coding agent1,000 requests a day, 40K in / 2K out, cached$810
- Overnight batch20,000 requests a day, 4K in / 0.4K out$3,360
Where to run it
1 host serve Kimi K2.8 Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Tencent TokenHubCloud kimi-k2.8-preview | $1.00 / $4.00 | kimi-k2.8-preview |
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
- Prompt caching
- Open weights
- License: Modified MIT LicenseRuntimes: 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 Tencent TokenHub.
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 4% less
- 14% less
- 29% less
- 89% less
Open-weight picks
- 1% less
- 51% less
- 55% less
- 61% less
Call it
Using Tencent TokenHub's API.
from litellm import completion
response = completion(
model="tencent/kimi-k2.8-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K2.8 Preview cost?
On Tencent TokenHub, Kimi K2.8 Preview costs $1.00 per million input tokens and $4.00 per million output tokens. Cached input costs $0.25 per million tokens.
Which APIs offer Kimi K2.8 Preview?
Kimi K2.8 Preview runs on 1 API: Tencent TokenHub.
What is Kimi K2.8 Preview's context window?
1M tokens, with up to 1M tokens in one reply.
Is Kimi K2.8 Preview being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Kimi K2.8 Preview?
Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (4% less), Gemini 3.8 Flash on Google AI Studio (14% less) and Inkling on DeepInfra (1% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Kimi K2.8 Preview's API model id?
Use kimi-k2.8-preview with Tencent TokenHub.
Sources
Raw catalog entry for kimi-k2.8-preview on Tencent TokenHub
{
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.5e-7,
"input_cost_per_token": 0.000001,
"input_cost_per_token_cache_hit": 2.5e-7,
"litellm_provider": "tencent",
"max_input_tokens": 1000000,
"max_output_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 0.000004,
"source": "https://www.tencentcloud.com/document/product/1300/78937",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": false
}