> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.empiriolabs.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.empiriolabs.ai/_mcp/server. # Kimi K2.7 Code > Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs. ![Kimi K2.7 Code](https://media.empiriolabs.ai/model-logos/kimi.png) [Moonshot AI](/providers/moonshot) · Text Generation `POST /v1/chat/completions` Kimi K2.7 Code is Moonshot's trillion-parameter agentic coding model with 256K context, always-on reasoning, and text, image, and video inputs. ## At a glance | Field | Value | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------- | | Model id | `kimi-k2-7-code` | | Model release date | 2026-06-16 | | Input modalities | Text, Image, Video | | Output modalities | Text | | Context window | 256K | | Weight precision | - | | Max output tokens | 131,072 | | Region | International | | Features | reasoning, function_calling, multimodal, agentic_coding, web_search | | Native inference | No | | New | No | | Structured output | JSON Schema | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/kimi-k2-7-code:generateContent` | | Alternate model ids | `kimi-k2.7-code`, `moonshotai/kimi-k2.7-code` | ## Pricing | Charge | Spec | Rate | | ---------- | ----------------------- | ------- | | Input | per 1M prompt tokens | \$0.95 | | Output | per 1M generated tokens | \$4.00 | | Web search | per call when invoked | \$0.015 | ## Example request ```bash curl https://api.empiriolabs.ai/v1/chat/completions \ -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ -H 'Content-Type: application/json' \ -d '{"model": "kimi-k2-7-code", "messages": [{"role":"user","content":"Hello"}]}' ``` ## Parameters | Parameter | Type | Required | Default | Description | | ----------------- | ------- | -------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------- | | `max_tokens` | number | no | `32768` | Maximum output tokens. Reasoning tokens count toward this limit. · Range: 1 – 262144 | | `stop` | string | no | - | Up to 4 strings where the model will stop generating further tokens. | | `tool_web_search` | boolean | no | false | Search the web for real-time information. Adds \$0.015 to the request cost for each invoked web search call. | | `max_tool_calls` | number | no | `5` | Max number of web searches the model can run in one request. Each search is billed separately. · Range: 1 – 20 | | `response_format` | enum | no | - | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide. | ## Notes Supports text, image, and video inputs with 256K context, function calling, JSON mode structured output, and built-in web search at \$0.015 per invoked call. Thinking is always on and cannot be disabled; reasoning tokens are billed as output tokens. Temperature and other sampling overrides are ignored because the model service uses fixed sampling settings. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact. **Per-tool billing (`usage.tool_usage`)** When this model invokes built-in tools inside a single request, the response carries a normalized `usage.tool_usage` map alongside the token counts. Tool counts are already factored into `cost_usd` and are surfaced for transparency. ## Variants ### `:variant1` | Field | Value | | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | Model id | `kimi-k2-7-code:variant1` | | Model release date | 2026-06-16 | | Region | Germany | | Context window | 256K | | Weight precision | - | | Max output tokens | 16,384 | | Features | reasoning, function_calling, multimodal, agentic_coding, cache, web_search | | Native inference | No | | Structured output | Not supported | | Supported endpoints | `POST /v1/chat/completions`, `POST /v1/responses`, `POST /v1/messages`, `POST /v1beta/models/kimi-k2-7-code:variant1:generateContent` | **Pricing** | Charge | Spec | Rate | | ------------------- | -------------------------- | ------------------- | | Input | per 1M prompt tokens | ~~\$0.95~~ \$0.8939 | | Output | per 1M generated tokens | ~~\$4.00~~ \$3.7131 | | Implicit cache read | per 1M cached input tokens | \$0.1788 | | Web Search (Linkup) | per call when invoked | \$0.013 | **Parameters** | Parameter | Type | Required | Default | Description | | -------------------- | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `max_tokens` | number | no | `16384` | Maximum output tokens. Reasoning tokens count toward this limit. · Range: 1 – 16384 | | `stop` | string | no | - | Up to 4 strings where the model will stop generating further tokens. | | `response_format` | object | no | - | OpenAI-compatible JSON mode or JSON schema response format. | | `web_search_linkup` | boolean | no | false | Optional web search powered by Linkup. When enabled, recent web sources are retrieved using your latest user message as the query and provided to the model as additional context. Adds \$0.013 per call when invoked on top of the model's normal token cost. Disabled by default. | | `disable_formatting` | boolean | no | false | Return the answer without the Sources list that web search adds. | --- *Machine-readable schema:* `GET https://api.empiriolabs.ai/v1/models/kimi-k2-7-code`.