Kimi K2 Thinking
Kimi K2 Thinking by Moonshot. Official list price: $0.6 per 1M input and $2.5 per 1M output tokens.
Your budget
Input:output ratio · Similar amounts of input and output
Purchasing power ranking
$100 · Kimi K2 Thinking · Balanced
Best price
SwiftRoute
−90%
providers
4
max −90%
Purchasing power ranking
The provider's published prices next to the vendor's official list.
| # | Provider | Input | Output | Cache | Uptime | Latency | Score | Tokens for budget | Save |
|---|---|---|---|---|---|---|---|---|---|
| — | Official price | $0.600 | $2.50 | — | — | — | — | 64.5M | 0% |
| 1 | Minimum top-up: $5· Nov 10, 2026 | $0.059 | $0.244 | — | 100.0% | 616 ms | 96 | 661M | −90% |
| 2 | Minimum top-up: ¥20· Nov 05, 2026 | $0.269 | $1.12 | — | 100.0% | 900 ms | 93 | 144M | −55% |
| 3 | Novita AIoperational · Nov 10, 2026 | $0.600 | $2.50 | $0.150 | 100.0% | 854 ms | 93 | 64.5M | 0% |
| 4 | Polza.aioperational · Nov 10, 2026 | $0.859 | $3.58 | $0.215 | 100.0% | 471 ms | 98 | 45.1M | -43% |
Some links on this site are partner links. They do not affect prices or ranking. Uptime and latency come from our own GET /models probes every 30 minutes, not a guarantee that the model is available.
Cost estimate
What one request and a month of traffic cost at the selected provider.
per request
$0
per month
$1.17
SwiftRoute · −90% · 1.20K / 500
Other models
Frequently asked questions
Answers are generated from the live quotes.
We collect Kimi K2 Thinking prices two ways: the official Moonshot list and quotes from providers our crawler checks daily. Providers in our catalogue sell Kimi K2 Thinking at $0.059 in / $0.244 out (90% below the official list). Everything is normalised to a blended cost at a chosen input:output ratio, so “Kimi K2 Thinking price per 1M tokens” means the same thing on every page.
What does the Kimi K2 Thinking API cost?
The official Moonshot list price is $0.600 per 1M input tokens and $2.50 per 1M output tokens.
How much does 1 million tokens of Kimi K2 Thinking cost?
1M input tokens cost $0.600, 1M output tokens — $2.50. With a 1:1 input/output load a million tokens works out to about $1.55. Chatbots with long context push the blended price down; code generation pushes it up.
Where is the Kimi K2 Thinking API cheapest?
Our measurements show SwiftRoute as the cheapest: 90% below the official price (sample listing). Quotes from 4 providers refresh daily — see the table above.
What is the Kimi K2 Thinking context window?
The context window is 200K tokens. Some vendors raise the price above a context threshold — check the plan notes.
How do I check that a provider key works?
The free checker sends a GET request to your endpoint's model list and reports status and latency. The key is not stored server-side.