MoonshotAI: Kimi K2 Thinking
moonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
Modalities
In / out per 1M$0.60 / $2.50
Context256K
ReleasedNov 6, 2025
Providers
2 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Google Vertex | $0.60 | $2.50 | Variable | 0.82s | 146 tps | 100% |
| $0.60 | $2.50 | $0.15 | 1.61s | 39 tps | 100% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Kimi K2 Thinking in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Kimi K2 Thinking costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.60
per 1M tokens
Output
$2.50
per 1M tokens
Cache read
$0.15
per 1M cached tokens
Included in every pass
Kimi K2 Thinking is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s2.0s4.0s6.0s8.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Google Vertex NovitaAI
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Google Vertex NovitaAI
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.53%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.57%
100% 97% 93% 90%
Oct 13, 2:50 PMNow
Apps
Tools that most often run Kimi K2 Thinking, by tokens this week.
Activity
15.4B tokens processed market-wide in the last month.
01.0B2.0B3.0B4.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Kimi K2 Thinking?
moonshotai/kimi-k2-thinking. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Kimi K2 Thinking hold?
262,144 tokens per request, of which up to 98,304 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Kimi K2 Thinking cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.60 per 1M input tokens and $2.50 per 1M output tokens.
Who built Kimi K2 Thinking?
MoonshotAI, in the Kimi family.
Explore
Other models your pass can call.
