Kimi K2.7
databricks-kimi-k2-7Pricing
List prices at Databricks, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.95 | $4.00 | |
| Cached input 80% off input | $0.19 | 80% off input | |
| Cache write, 5 minutes | $0.95 |
What it costs a month
At Databricks list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$517
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$418
- Coding agent1,000 requests a day, 40K in / 2K out, cached$742
- Overnight batch20,000 requests a day, 4K in / 0.4K out$3,240
Where to run it
1 host serve Kimi K2.7. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DatabricksCloud databricks-kimi-k2-7 | $0.95 / $4.00 | databricks-kimi-k2-7 |
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
- ImagesText
- 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 Databricks.
Smaller Moonshot AI models
No cheaper Moonshot AI model keeps its key capabilities.
Other frontier labs
- 1% less
- 12% less
- 27% less
- 88% less
Open-weight picks
- 60% less
- 63% less
- 69% less
- 72% less
Model line
Newer and older versions, at each lab's own price.
Call it
Using Databricks's API.
from litellm import completion
response = completion(
model="databricks/databricks-kimi-k2-7",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Kimi K2.7 cost?
On Databricks, Kimi K2.7 costs $0.95 per million input tokens and $4.00 per million output tokens. Cached input costs $0.19 per million tokens.
Which APIs offer Kimi K2.7?
Kimi K2.7 runs on 1 API: Databricks.
What is Kimi K2.7's context window?
262K tokens, with up to 262K tokens in one reply.
Is Kimi K2.7 being retired?
It has been retired: Databricks retired it on 30 Oct 2026.
Is there a newer version of Kimi K2.7?
Yes. Kimi K3.1 is the newest model in this line.
What are cheaper alternatives to Kimi K2.7?
Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (1% less), Gemini 3.8 Flash on Google AI Studio (12% less) and Kimi K2.7 Code on CLF AI Gateway (60% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Kimi K2.7's API model id?
Use databricks-kimi-k2-7 with Databricks.
Sources
Raw catalog entry for databricks-kimi-k2-7 on Databricks
{
"cache_creation_input_token_cost": 9.4997e-7,
"cache_read_input_token_cost": 1.8998e-7,
"deprecation_date": "2026-10-30",
"deprecation_source": "https://docs.databricks.com/aws/en/machine-learning/retired-models-policy",
"input_cost_per_token": 9.4997e-7,
"input_dbu_cost_per_token": 0.000013571,
"litellm_provider": "databricks",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"metadata": {
"notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields."
},
"mode": "chat",
"output_cost_per_token": 0.00000400001,
"output_dbu_cost_per_token": 0.000057143,
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"successor_model": "databricks/databricks-kimi-k3",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
}