Kimi K2.5 API Pricing
Moonshot · Mid-tier · Modified MIT · released 2025-12. Prices in USD per 1 million tokens. Data snapshot: 2026-09-11.
- Input: $0.45 per 1M tokens
- Output: $2.25 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.07
- Context window: 262K
- Arena ELO: 1451 (as of 2026-09-02)
- Available on: Direct API, OpenRouter (curated by hand, verify with the provider)
- AWS Bedrock regions: ap-northeast-1, us-east-1, us-east-2, us-west-2
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0018 | $0.0015 | $146 |
| Knowledge Q&A | 2,000 / 800 | $0.0027 | $0.0022 | $217 |
| Meeting Summary | 10,000 / 1,200 | $0.0072 | $0.0068 | $682 |
| Marketing Content | 2,500 / 1,800 | $0.0052 | $0.0050 | $499 |
| Coding Task | 3,000 / 2,000 | $0.0059 | $0.0053 | $528 |
| Invoice Processing | 1,500 / 600 | $0.0020 | $0.0019 | $185 |
| Call Summary | 2,000 / 700 | $0.0025 | $0.0024 | $240 |
| Agent Workflow | 6,000 / 3,000 | $0.0095 | $0.0079 | $785 |
Kimi K2.5 pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 6 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-11 via OpenRouter — negotiated rates, committed-use discounts and provisioned capacity are not shown.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| SiliconFlow (the price shown above) — int4 | $0.45 | $2.25 |
| AtlasCloud — int4 | $0.49 | $2.50 |
| Novita | $0.57 | $2.85 |
| Amazon Bedrock | $0.60 | $3.00 |
| Phala | $0.60 | $3.00 |
| Venice | $0.53 | $3.33 |
Models comparable to Kimi K2.5
The nearest Mid-tier models on Arena ELO, so a substitution is compared on quality as well as price.
- Gemini 3.5 Flash Lite (Google) — $0.30 in / $2.50 out per 1M, Arena ELO 1457
- Grok 4.6 (xAI) — $2.00 in / $6.00 out per 1M, Arena ELO 1461
- Kimi K2.6 (Moonshot) — $0.95 in / $4.00 out per 1M, Arena ELO 1461
- Qwen3.5 397B A17B (Alibaba) — $0.55 in / $3.50 out per 1M, Arena ELO 1441
Common questions about Kimi K2.5 pricing
- How much does Kimi K2.5 cost?
- Kimi K2.5 costs $0.45 per million input tokens and $2.25 per million output tokens on the API.
- Does Kimi K2.5 offer batch or cached pricing?
- Prompt-cache reads cost $0.07/M input tokens. No batch pricing is published.
- What would Kimi K2.5 cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Kimi K2.5 costs about $180 at list prices.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for Kimi K2.5 in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server