Kimi K3 (US) pricing, context window and limits
Kimi K3 (US) costs $3.3 per million input tokens and $16.5 per million output tokens at Amazon Bedrock list price. It accepts up to 1,048,576 tokens of context and returns up to 128,000 tokens.
- Model id
bedrock/us.moonshotai.kimi-k3 - Snapshot
What does Kimi K3 (US) cost?
| Input | $3.3 |
|---|---|
| Output | $16.5 |
| Cached input (read) | $0.33 |
| Cache write | $4.125 |
US dollars per million tokens. A dash means no price is published.
How much can Kimi K3 (US) read and write?
| Context window | 1,048,576 |
|---|---|
| Max output | 128,000 |
What can Kimi K3 (US) do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning | Yes |
| Input | text, image |
| Output | text |
What does a request to Kimi K3 (US) cost?
| A typical request: 1,000 tokens in, 500 out | $0.012 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.05 |
| 1,000 typical requests | $11.55 |
| 1 million tokens in and 1 million out | $19.8 |
Input read from the provider's prompt cache costs $0.33 per million tokens instead of $3.3, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.0086 instead of $0.012.
Among 191 Amazon Bedrock models with a published price, Kimi K3 (US) is the 132nd cheapest by input price. Its context window is the 26th largest of 191. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call Kimi K3 (US) through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/us.moonshotai.kimi-k3. DVARA, the AI governance platform, 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 is counted as costing nothing. 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 K2 Thinking$0.6 in · $2.5 out · 262K context
- Kimi K3 (Global)$3 in · $15 out · 1.05M context
- Pixtral Large (25.02) (US)$2 in · $6 out · 128K context
- GPT-5.6 Luna (US)$0.22 in · $1.32 out · 1.05M context
- Llama 4 Scout 17B Instruct (US)$0.17 in · $0.66 out · 10M context
- GPT-5.6 Sol (US)$4.4 in · $22 out · 1.05M context
- Llama 4 Maverick 17B Instruct (US)$0.24 in · $0.97 out · 1M context
- GPT-5.6 Terra (US)$2.2 in · $13.2 out · 1.05M context
- Llama 3.3 70B Instruct (US)$0.72 in · $0.72 out · 128K context
- GPT-6 Astra (US)$11 in · $55 out · 1.05M context
- Llama 3.1 8B Instruct (US)$0.22 in · $0.22 out · 128K context
Which models from other providers are similar to Kimi K3 (US)?
These are the closest in context window and input price, one per provider.
- Kimi K3Moonshot AI · $3 in · $15 out · 1.05M context
- Claude Sonnet 4.5 (latest)Anthropic · $3 in · $15 out · 1M context
- GPT-5.6OpenAI · $4 in · $20 out · 1.05M context
- Qwen3.7 MaxAlibaba Qwen · $2.5 in · $7.5 out · 1M context
- Gemini 3.1 Pro PreviewGoogle Gemini · $2 in · $12 out · 1.05M context