Capabilities
7-day heat trend
−15.5%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 19% of tracked models
- Faster than 8% of tracked models
- Efficiency rank: #539 of 1105
Best suited for
Mixed text, image, audio and document workloads that benefit from one model across modalities.
About moonshotai/Kimi-K2.5
Kimi K2.5 on Together is a multimodal Moonshot model for long-context reasoning, coding, and vision workflows.
moonshotai/Kimi-K2.5 is a Multimodal model from Together AI (US). HotON.ai tracks it at $0.50 per 1M input tokens and $2.80 per 1M output tokens, with a 262K-token context window, ~124 tokens/sec throughput and 96.7% availability. Its composite efficiency score is 89/100 at an estimated $0.002 per successful task.
Compare moonshotai/Kimi-K2.5
Related market news
Frequently asked questions
How much does moonshotai/Kimi-K2.5 cost per 1M tokens?+
moonshotai/Kimi-K2.5 is tracked at $0.50 per 1M input tokens and $2.80 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $2.22 per 1M tokens. Figures are illustrative demo data.
What is moonshotai/Kimi-K2.5 best for?+
Mixed text, image, audio and document workloads that benefit from one model across modalities.
How fast is moonshotai/Kimi-K2.5?+
moonshotai/Kimi-K2.5 delivers about 124 tokens/sec with 96.7% tracked availability, suitable for latency-sensitive, real-time applications.
Is moonshotai/Kimi-K2.5 cheaper than other AI models?+
Within the HotON.ai tracked set, moonshotai/Kimi-K2.5 is cheaper than 19% of models on input price and ranks #539 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.