Kimi K2.5
Moonshot AIUpdated May 2026. Kimi K2.5 by Moonshot AI: $0.6/M cache-miss input, $2.00/M output tokens. 128K context, 8K max output. Vision & Function Calling. Free calculator + compare 40+ models.
Input Price
$0.6
cache miss / 1M tokens
Output Price
$2.00
per 1M tokens
Context Window
128K
tokens
Specifications
| Provider | Moonshot AI |
| Model ID | kimi-k2-5 |
| Input Price | $0.6 / 1M cache-miss tokens |
| Output Price | $2 / 1M tokens |
| Context Window | 128K tokens |
| Max Output | 8K tokens |
| Capabilities | textvisionfunction_calling |
| Release Date | 2026-01 |
| Pricing Source | Official Moonshot AI pricing |
| Price Verified | 2026-04-28 |
| Notes | 76.8% SWE-bench. Strongest open-source model. Agent Swarm support. |
Monthly Cost Estimates
Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.
| Daily Tokens | Monthly Cost | Annual Cost |
|---|---|---|
| 10K | $0.39 | $4.68 |
| 50K | $1.95 | $23.40 |
| 100K | $3.90 | $46.80 |
| 500K | $19.50 | $234.00 |
| 1.0M | $39.00 | $468.00 |
About Kimi K2.5
Kimi K2.5 is a large language model by Moonshot AI. It features a 128K token context window with up to 8K tokens of output per request. The model supports 3 capabilities: text, vision, function_calling.
At $0.6 per million cache-miss input tokens and $2 per million output tokens, Kimi K2.5 is positioned as a cost-effective option in the Moonshot AI lineup. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.
Kimi K2.5 Key Details
- Pricing: $0.6/M cache-miss input tokens, $2/M output tokens
- Context window: 128K tokens — good for standard conversations and tasks
- Max output: 8K tokens per response
- Capabilities: text, vision, function_calling
- Highlights: 76.8% SWE-bench. Strongest open-source model. Agent Swarm support.
- Released: 2026-01
Similar Price Range
Related Tools
FAQ
How much does Kimi K2.5 cost?
Kimi K2.5 costs $0.6 per million cache-miss input tokens and $2 per million output tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $4.80/month before cache-hit savings.
What is Kimi K2.5's context window?
Kimi K2.5 supports a context window of 128K tokens. This means your combined input prompt and output response can be up to 128K tokens. The maximum output per response is 8K tokens.
Is Kimi K2.5 good for my use case?
Kimi K2.5 supports text, vision, function_calling. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.