Capabilities
7-day heat trend
−14.1%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 17% of tracked models
- Faster than 22% of tracked models
- Efficiency rank: #301 of 1105
Best suited for
Mixed text, image, audio and document workloads that benefit from one model across modalities.
About accounts/fireworks/models/kimi-k2p5
Kimi K2.5 on Fireworks is a serverless multimodal model for agentic reasoning and vision tasks.
accounts/fireworks/models/kimi-k2p5 is a Multimodal model from Fireworks AI (US). HotON.ai tracks it at $0.60 per 1M input tokens and $3.00 per 1M output tokens, with a 262K-token context window, ~132 tokens/sec throughput and 96.4% availability. Its composite efficiency score is 89/100 at an estimated $0.003 per successful task.
Compare accounts/fireworks/models/kimi-k2p5
Related market news
Frequently asked questions
How much does accounts/fireworks/models/kimi-k2p5 cost per 1M tokens?+
accounts/fireworks/models/kimi-k2p5 is tracked at $0.60 per 1M input tokens and $3.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $2.40 per 1M tokens. Figures are illustrative demo data.
What is accounts/fireworks/models/kimi-k2p5 best for?+
Mixed text, image, audio and document workloads that benefit from one model across modalities.
How fast is accounts/fireworks/models/kimi-k2p5?+
accounts/fireworks/models/kimi-k2p5 delivers about 132 tokens/sec with 96.4% tracked availability, suitable for latency-sensitive, real-time applications.
Is accounts/fireworks/models/kimi-k2p5 cheaper than other AI models?+
Within the HotON.ai tracked set, accounts/fireworks/models/kimi-k2p5 is cheaper than 17% of models on input price and ranks #301 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.