Kimi K2.7 Code: API Pricing, Context Window & Benchmarks
Kimi K2.7 Code is a language model from MoonshotAI, released in June 2026, with multimodal input, a 262K-token context window, and pricing from $0.740/M input and $3.50/M output.
Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6. It improves real-world long-horizon coding task completion, instruction following, and token efficiency while reducing thinking-token usage by approximately
Kimi K2.7 Code benchmarks
Rankings
Quality Tracker
Kimi K2.7 Code Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Jul 18 2026Kimi K2.7 Code pricing
Providers
Kimi K2.7 Code starts at $0.740 per million input tokens and $3.50 per million output tokens via DeepInfra. See all 5 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Workload 1M + 100K | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|---|---|
 DeepInfra | $0.740 | — | $3.50 | $1.09 | 262.1K/131.1K | 0.77/0.98 | 116/16 | 100.00%(33) | / |
 Fireworks | $0.950 | — | $4.00 | $1.35 | 262.1K/131.1K | 0.92/16.85 | 334/105 | 44.83%(29) | / |
 Moonshot AI | $0.950 | $0.190 | $4.00 | $1.35 | 262.1K/262.1K | 1.42/2.87 | 102/14 | 100.00%(37) | / |
 Novita | $0.950 | — | $4.00 | $1.35 | 262.1K/262.1K | 1.50/2.95 | 160/135 | 56.25%(48) | / |
 Together | $0.950 | — | $4.00 | $1.35 | 262.1K/131.1K | 0.36/0.36 | 328/328 | 6.67%(15) | / |
Workload cost uses 1M input tokens plus 100K output tokens at published list prices without assuming a cache hit. Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
Kimi K2.7 Code model size
Kimi K2.7 Code has 1 trillion parameters. See how it compares to other models in the same parameter range.
Kimi K2.7 Code context window
Input and output token limits for Kimi K2.7 Code, plus how it ranks on long-context understanding.
Kimi K2.7 Code API
Run a request to see the response
Use it in your code
Billed at $0.74 input / $3.50 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="kimi-k2.7-code",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Kimi K2.7 Code latency
Kimi K2.7 Code time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
Kimi K2.7 Code examples
Recent arena outputs from Kimi K2.7 Code, picked from the highest-ranked matchups.
Kimi K2.7 Code license
Kimi K2.7 Code is released under the Modified MIT License license, which restricts commercial use, has 1.0T parameters.
- License
- Modified MIT License
- Non-commercial
- Parameters
- 1.0T
Kimi K2.7 Code resources
Official sources for Kimi K2.7 Code: api documentation, official playground, source repository.
Kimi K2.7 Code vs other models
The most-compared alternatives to Kimi K2.7 Code are GLM-5.1, GPT-5.1 High, Qwen3.7 Max. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Kimi K2.7 Code
Models ranked just above and below Kimi K2.7 Code by LLM Stats score.
FAQ
Common questions about Kimi K2.7 Code.