Calculate the cost of using Kimi-K2.5 from Together AI for your AI applications
Pricing data last updated:
Mode: Chat
Max: 256,000 tokens
Max: 256,000 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Kimi-K2.5 is a chat model from Together AI, one of 32 chat models they offer. It is priced at $0.50 per 1M input tokens and $2.80 per 1M output tokens, ranking 1055 out of 2168 chat models by cost and cheaper than 51% of models in this category. Kimi-K2.5 supports vision, function calling, reasoning — one of only 10 chat models with this combination. Its 256K-token context window is in the top 27% 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 256,000 input tokens. The maximum output length is 256,000 tokens.
At $0.50 per 1M input tokens and $2.80 per 1M output tokens, Kimi-K2.5 ranks 1055 out of 2168 chat models by input cost. It is more affordable compared to the median of $0.55 for chat models, and is cheaper than 51% of models in this category.
Kimi-K2.5 is one of 32 Together AI chat models, one of only 10 chat models combining function calling, reasoning, vision. its 256K-token context window places it in the top 27% of chat models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs Kimi-K2.5 |
|---|---|---|---|---|
| moonshotai.kimi-k2.5 | AWS Bedrock | $0.60 | $3.03 | +20% |
| qwen3-vl-235b-a22b-thinking | Dashscope | $0.40 | $4.00 | -20% |
| gemini-3-flash-preview | Vertex AI | $0.50 | $3.00 | 0% |
Similar chat models from other providers
Yes. Kimi-K2.5 costs $0.50 per 1M input tokens compared to moonshotai.kimi-k2.5's $0.60 per 1M input tokens, making it 20% more affordable. Both are chat models and share support for vision, function calling, reasoning.
Kimi-K2.5 input pricing is $0.50 per 1M tokens, which is 9% below the median of $0.55 for chat models. It ranks 1055 out of 2168 chat models by input cost, making it cheaper than 51% of models in this category. For output, it costs $2.80 per 1M tokens compared to the median of $1.44.
Among Together AI's 32 chat models, Kimi-K2.5 ranks 15 by input cost. Its combination of function calling, reasoning, vision is shared by only 9 other chat models.
The most comparable chat models to Kimi-K2.5 are: moonshotai.kimi-k2.5 from AWS Bedrock ($0.60/1M input tokens); qwen3-vl-235b-a22b-thinking from Dashscope ($0.40/1M input tokens); gemini-3-flash-preview from Vertex AI ($0.50/1M input tokens); gemini-3-flash-preview from Google Gemini ($0.50/1M 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-K2.5 supports up to 256,000 input tokens, placing it in the top 27% of chat models by context window size (rank 544 of 2093). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
You can monitor Together AI service health in real time on the Bifrost Together AI Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
Kimi-K2.5 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 $0.50 and generating 1M output tokens costs $2.80.
