Kimi K2 Thinking pricing, context window and limits
Kimi K2 Thinking costs $0.6 per million input tokens and $2.5 per million output tokens at Amazon Bedrock list price. It accepts up to 262,144 tokens of context and returns up to 16,000 tokens.
- Model id
bedrock/moonshot.kimi-k2-thinking - Snapshot
What does Kimi K2 Thinking cost?
| Input | $0.6 |
|---|---|
| Output | $2.5 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can Kimi K2 Thinking read and write?
| Context window | 262,144 |
|---|---|
| Max output | 16,000 |
What can Kimi K2 Thinking do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text |
| Output | text |
What does a request to Kimi K2 Thinking cost?
| A typical request: 1,000 tokens in, 500 out | $0.0019 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.0085 |
| 1,000 typical requests | $1.85 |
| 1 million tokens in and 1 million out | $3.1 |
Among 199 Amazon Bedrock models with a published price, Kimi K2 Thinking is the 72nd cheapest by input price. Its context window is the 117th largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Kimi K2 Thinking through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/moonshot.kimi-k2-thinking. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.
Which other Amazon Bedrock models are there?
- Kimi K2.5$0.6 in · $3 out · 262K context
- Kimi K3 (Global)$3 in · $15 out · 1.05M context
- Kimi K3 (US)$3.3 in · $16.5 out · 1.05M context
- Voxtral Small 24B 2507$0.1 in · $0.3 out · 33K context
- Voxtral Mini 3B 2507$0.04 in · $0.04 out · 33K context
- NVIDIA Nemotron Nano 12B v2 VL BF16$0.2 in · $0.6 out · 131K context
- Pixtral Large (25.02)$2 in · $6 out · 128K context
- NVIDIA Nemotron Nano 3 30B$0.06 in · $0.24 out · 262K context
- Mistral Large 3$0.5 in · $1.5 out · 262K context
- NVIDIA Nemotron Nano 9B v2$0.06 in · $0.23 out · 131K context
- Ministral 3 8B$0.15 in · $0.15 out · 128K context
- NVIDIA Nemotron 3 Super 120B A12B$0.15 in · $0.65 out · 262K context
Which models from other providers are similar to Kimi K2 Thinking?
These are the closest in context window and input price, one per provider.
- Mistral Large 3Mistral AI · $0.5 in · $1.5 out · 262K context
- GLM-4.6Zhipu GLM · $0.6 in · $2.2 out · 205K context
- Qwen3-Coder 480B-A35B InstructAlibaba Qwen · $0.861 in · $3.441 out · 262K context
- Kimi K2.6Moonshot AI · $0.95 in · $4 out · 262K context
- Grok Build 0.1xAI Grok · $1 in · $2 out · 256K context