Kimi K2.5
The widely used Kimi K2.5 open-weight MoE with thinking, available via OpenRouter and across inference gateways.
Source: Moonshot AI pricing, Kimi models, Metadata verification, Field resolution verification
- Text
- Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate |
|---|---|
| Input | $0.49 / M |
| Output | $2.5 / M |
| Cache read | $0.2 / M |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Compare providers
The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.
| Platform | Region | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|---|
ModelrunLowest | - | $0.4 | $1.9 | $0.09 | - | via OpenRouter |
Chutes | - | $0.44 | $2 | $0.22 | - | via OpenRouter |
DeepInfra | - | $0.45 | $2.25 | $0.07 | - | via OpenRouter |
SiliconFlow | - | $0.45 | $2.25 | $0.07 | - | via OpenRouter |
AtlasCloud | - | $0.49 | $2.5 | $0.2 | - | via OpenRouter |
DigitalOcean | - | $0.5 | $2.7 | $0.203 | - | via OpenRouter |
StreamLake | - | $0.54 | $2.7 | $0.09 | - | via OpenRouter |
Together AI | - | $0.5 | $2.8 | - | - | Direct |
Novita | - | $0.57 | $2.85 | $0.095 | - | via OpenRouter |
AWS Bedrock | $0.6 | $3 | - | ✓ | Direct | |
Azure AI Foundry | - | $0.6 | $3 | - | - | Direct |
Fireworks AI | - | $0.6 | $3 | $0.1 | - | Direct |
AWS Bedrock | - | $0.6 | $3 | - | - | via OpenRouter |
Moonshot AI | - | $0.6 | $3 | $0.1 | - | via OpenRouter |
Phala | - | $0.6 | $3 | $0.22 | - | via OpenRouter |
Venice | - | $0.532 | $3.33 | $0.209 | - | via OpenRouter |
Azure AI Foundry (Fireworks) | - | $0.66 | $3.3 | $0.11 | - | Direct |
Azure AI Foundry · Data zone | - | $0.66 | $3.3 | - | - | Direct |
Some hosts price by region. Shown rates match the selected region.
Price history
Has this model gotten cheaper or more expensive?
More from Moonshot AI (Kimi)
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Kimi K2.5 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.


