Kimi-K2.7-Code
By moonshotai. 1.03 trillion parameters, a context window of 262,144 tokens and the licence other.
Facts
- Released
- 2026-06-11 the day the repository was first published on Hugging Face Hugging Face, read
- Licence
- other the licence the model card declares Hugging Face, read
- Open weights
- Yes the weights are published in this Hugging Face repository Hugging Face, read
- Parameters
- 1.03 trillion counted from the safetensors weight files Hugging Face, read
- Active parameters
- 33.3 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
- Knowledge cutoff
- Unknown
- Context window
- 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
- Longest output
- Unknown
- Tool calling
- Unknown
- Structured output
- Unknown
- Reasoning controls
- Unknown
- Inputs and outputs
- text, image in, text out Hugging Face, read
- Good for
- Vision: Hugging Face files it under image-text-to-text Hugging Face, read
- Coding: the maker's name for the model marks it for code Hugging Face, read
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| Inceptron | 0.660 USD | 3.40 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Kilo Gateway | 0.671 USD | 3.35 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| NanoGPT | 0.671 USD | 3.35 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| OpenRouter | 0.671 USD | 3.35 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Deep Infra | 0.680 USD | 3.40 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| IteraCompute | 0.690 USD | 3.29 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Ambient | 0.690 USD | 3.49 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| CoreWeave | 0.710 USD | 3.50 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| ai& | 0.750 USD | 3.50 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| SiliconFlow | 0.859 USD | 3.80 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| inferenceapis | 0.890 USD | 4.42 USD | 262,144 | LiteLLM, read | |
| Abacus | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Baseten | 0.950 USD | 4.00 USD | 262,000 | older than 30 days; check the provider | models.dev, read |
| CommandCode | 0.950 USD | 4.00 USD | 256,000 | older than 30 days; check the provider | models.dev, read |
| HPC-AI | 0.950 USD | 4.00 USD | 256,000 | older than 30 days; check the provider | models.dev, read |
| Hugging Face | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Nebius Token Factory | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Novita AI | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Ofox | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Pioneer | 0.950 USD | 4.00 USD | 256,000 | older than 30 days; check the provider | models.dev, read |
| Together AI | 0.950 USD | 4.00 USD | 262,144 | LiteLLM, read | |
| Vercel AI Gateway | 0.950 USD | 4.00 USD | 256,000 | older than 30 days; check the provider | models.dev, read |
| ZenMux | 0.950 USD | 4.00 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| OpenReason | 1.00 USD | 4.22 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| TensorX | 1.25 USD | 4.50 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
Run it on your own hardware
Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.
| Quantization | Weights | Memory at 8,192 tokens | Memory at 32,768 tokens |
|---|---|---|---|
| UD-IQ1_M | 283 GiB | 298 GiB | 300 GiB |
| UD-IQ2_XXS | 296 GiB | 312 GiB | 313 GiB |
| UD-IQ2_M | 296 GiB | 312 GiB | 314 GiB |
| UD-Q2_K_XL | 316 GiB | 333 GiB | 335 GiB |
| UD-IQ3_S | 390 GiB | 411 GiB | 412 GiB |
| UD-Q3_K_M | 432 GiB | 454 GiB | 456 GiB |
| UD-Q3_K_XL | 432 GiB | 455 GiB | 456 GiB |
| UD-Q4_K_XL | 544 GiB | 572 GiB | 573 GiB |
Start it with a local runtime
- Ollama
ollama run hf.co/unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M - LM Studio
lms get unsloth/Kimi-K2.7-Code-GGUF lms server start - llama.cpp server
llama-server -hf unsloth/Kimi-K2.7-Code-GGUF:UD-IQ1_M --jinja - vLLM
vllm serve moonshotai/Kimi-K2.7-Code - SGLang
sglang serve --model-path moonshotai/Kimi-K2.7-Code --port 30000
Use it from your harness
Set up for Abacus with the model moonshotai/Kimi-K2.7-Code. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"abacus": {
"npm": "@ai-sdk/openai-compatible",
"name": "Abacus",
"options": {
"baseURL": "https://routellm.abacus.ai/v1",
"apiKey": "{env:ABACUS_API_KEY}"
},
"models": {
"moonshotai/Kimi-K2.7-Code": {
"name": "Kimi-K2.7-Code"
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"abacus": {
"baseUrl": "https://routellm.abacus.ai/v1",
"api": "openai-completions",
"apiKey": "$ABACUS_API_KEY",
"models": [
{
"id": "moonshotai/Kimi-K2.7-Code"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and Abacus documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and Abacus documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Other ways to reach it
- ai&, model
moonshotai/kimi-k2.7-code - Ambient, model
moonshotai/kimi-k2.7-code - Baseten, model
moonshotai/Kimi-K2.7-Code - CommandCode, model
moonshotai/Kimi-K2.7-Code - DeepInfra, model
moonshotai/Kimi-K2.7-Code - HPC-AI, model
moonshotai/kimi-k2.7-code - Hugging Face, model
moonshotai/Kimi-K2.7-Code - Inceptron, model
moonshotai/Kimi-K2.7-Code - IteraCompute, model
moonshotai/kimi-k2.7-code - Kilo Gateway, model
moonshotai/kimi-k2.7-code - NanoGPT, model
moonshotai/kimi-k2.7-code
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Results the maker published on the model card published by moonshotai Hugging Face, read
Two more publishers are linked, never copied, because their terms do not allow it:
- Artificial Analysis publishes its own intelligence, speed and price measurements.
- OpenRouter lists current prices and uptime for each provider it routes to.
Sources of this page
- huggingface.co/api/models/moonshotai/Kimi-K2.7-Code, read
- huggingface.co/moonshotai/Kimi-K2.7-Code/raw/main/config.json, read
- huggingface.co/api/models/unsloth/Kimi-K2.7-Code-GGUF/tree/main, read
- models.dev/api.json, read
- github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json, read
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.