Calculate the cost of using Kimi-K2-Thinking from Gmi for your AI applications
Pricing data last updated:
Mode: Chat
Max: 262,144 tokens
Max: 16,384 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Kimi-K2-Thinking is a chat model from Gmi, one of 17 chat models they offer. It is priced at $0.80 per 1M input tokens and $1.20 per 1M output tokens, ranking 1353 out of 2292 chat models by cost and cheaper than 40% of models in this category. Its 262K-token context window is in the top 25% among chat models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 262,144 input tokens. The maximum output length is 16,384 tokens.
At $0.80 per 1M input tokens and $1.20 per 1M output tokens, Kimi-K2-Thinking ranks 1353 out of 2292 chat models by input cost. It is more expensive compared to the median of $0.55 for chat models, and is cheaper than 40% of models in this category.
Kimi-K2-Thinking is one of 17 Gmi chat models, its 262K-token context window places it in the top 25% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs Kimi-K2-Thinking |
|---|---|---|---|---|
| amazon.nova-pro-v1:0 | AWS Bedrock | $0.80 | $3.20 | 0% |
| anthropic.claude-3-5-haiku-20241022-v1:0 | AWS Bedrock | $0.80 | $4.00 | 0% |
| anthropic.claude-haiku-4-5-20251001-v1:0 | AWS Bedrock | $1.00 | $5.00 | +25% |
Similar chat models from other providers
No. Kimi-K2-Thinking costs $0.80 per 1M input tokens while amazon.nova-pro-v1:0 costs $0.80 per 1M input tokens, making amazon.nova-pro-v1:0 0% more affordable for input. However, Kimi-K2-Thinking may offer different capabilities or performance characteristics that justify the price difference.
Kimi-K2-Thinking input pricing is $0.80 per 1M tokens, which is 45% above the median of $0.55 for chat models. It ranks 1353 out of 2292 chat models by input cost, making it cheaper than 40% of models in this category. For output, it costs $1.20 per 1M tokens compared to the median of $1.50.
Among Gmi's 17 chat models, Kimi-K2-Thinking ranks 8 by input cost.
The most comparable chat models to Kimi-K2-Thinking are: amazon.nova-pro-v1:0 from AWS Bedrock ($0.80/1M input tokens); anthropic.claude-3-5-haiku-20241022-v1:0 from AWS Bedrock ($0.80/1M input tokens); anthropic.claude-haiku-4-5-20251001-v1:0 from AWS Bedrock ($1.00/1M input tokens); anthropic.claude-haiku-4-5@20251001 from AWS Bedrock ($1.00/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
Kimi-K2-Thinking supports up to 262,144 input tokens, placing it in the top 25% of chat models by context window size (rank 433 of 2159). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
Kimi-K2-Thinking is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.80 and generating 1M output tokens costs $1.20.
