kimi-k2Google LLC (Vertex AI)
- api
- chat
- hosting
- US
- model lab
- Moonshot AI
- weights
- open
- added
- July 2025
- model id
- vertex/kimi-k2
capabilities 4/8
- input
- $0.60
- output
- $2.50
- cache write
- $2.50
- cache read
- $0.06
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0850 |
| 1M in + 100K out | $0.85 |
| 10M in + 1M out | $8.50 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| eval | Score as a share of 100 | /100 |
|---|---|---|
| Math Index | 94.7 | |
| AIME 2025 | 94.7 | |
| τ²-Bench | 93.0 | |
| LiveCodeBench | 85.3 | |
| MMLU Pro | 84.8 | |
| GPQA Diamond | 83.8 | |
| Terminal-Bench Hard | 31.1 | |
| Humanity's Last Exam | 23.8 | |
| Intelligence Index | 22.0 | |
| 9 evals | mean | 68.1 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-11-06.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Vertex AI Data Governance
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
vertex/kimi-k2this id pins the google llc (vertex ai) deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="vertex/kimi-k2", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Kimi K2 Thinking is an open-source model that operates as a "thinking agent," reasoning step-by-step while using tools to achieve state-of-the-art performance on various benchmarks. It is capable of executing up to 200-300 sequential tool calls without human intervention, allowing it to solve complex problems across a wide range of tasks. The model uses Quantization-Aware Training (QAT) to support INT4 inference, which provides a roughly 2x improvement in generation speed.
questions 6
How much does kimi-k2 cost?
What is the context window of kimi-k2?
How does kimi-k2 perform on benchmarks?
What can kimi-k2 do?
How do I use kimi-k2 with the OpenAI SDK?
Can I run kimi-k2 through Requesty?
more from google llc (vertex ai) 8
| endpoint | ctx | in /M |
|---|---|---|
| gemini-3.8-flash | 1.0M | $0.83 |
| gemini-3.8-flash | 1.0M | $0.75 |
| claude-fable-5.1 | 1M | $11.00 |
| claude-fable-5.1 | 1M | $10.00 |
| gemini-3.7-flash | 1.0M | $0.75 |
| gemini-3.7-flash | 1.0M | $0.83 |
| claude-opus-5 | 1M | $5.50 |
| claude-opus-5 | 1M | $5.50 |
call kimi-k2 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology