Last refreshed 2026-06-15. Next refresh: weekly.
Why use Kimi K2 Thinking on GCP Vertex AI?
GCP Vertex AI offers Kimi K2 Thinking with pay-as-you-go pricing at $0.60/1M input tokens. Vertex AI is Google Cloud's managed AI platform, offering access to Gemini models and hundreds of partner models alongside tools for fine-tuning, grounding, vector search, and end-to-end MLOps pipelines.
Compare Kimi K2 Thinking across 7 providers to find the best fit for your use caseInput / 1M
$0.60
Output / 1M
$2.50
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install google-cloud-aiplatformAuth
export GOOGLE_CLOUD_PROJECT=...Call
import os
import vertexai
from vertexai.generative_models import GenerativeModel
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")Model ID
kimi-k2-thinkingRequest example
import os
import vertexai
from vertexai.generative_models import GenerativeModel
# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("kimi-k2-thinking")
response = model.generate_content("Hello")
print(response.text)Gotchas
- For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
- The examples expect GOOGLE_CLOUD_PROJECT; rename it only if your application config maps the new variable.
Compare Kimi K2 Thinking Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.60 | $2.50 |
| GCP Vertex AI | $0.60 | $2.50 |
| NVIDIA NIM | — | — |
| AWS Bedrock | $0.60 | $2.50 |
| OpenRouter | $0.60 | $2.50 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.60 |
| Output tokens | $2.50 |
Capabilities
ReasoningStructured Outputs
About Kimi K2 Thinking
Extended thinking variant of Kimi K2 with native reasoning capabilities. 256K context.
Model Specs
Released2025-01-01
Parameters1T (32B active)
Context256k
ArchitectureDecoder Only