Kimi K2.5
DeprecatedKimi K2.5 is Moonshot AI (Kimi)'s language model with a 262K context window and up to 236K output tokens, available from 14 providers, starting at $0.45 / 1M input and $2.25 / 1M output. An updated iteration of Kimi K2 with enhanced reasoning, vision, and tool-use capabilities, supporting implicit caching for efficient inference.
| Specifications | |
|---|---|
moonshot-kimi-k2-5 | |
| Language | |
| Deprecated | |
| Moonshot AI (Kimi) | |
| 262K tokens | |
| 236K tokens | |
| ImageTextVideo | |
| Text | |
| default | |
| 1.06T | |
| 2,753 | |
| 5,222,216 | |
| 9,851,195 | |
| · 7 months ago | |
| Benchmarks | |
|---|---|
| Intelligence Index | #87 |
| Coding Index | #70 |
| GPQA | #60 |
| HLE | #64 |
| IFBench | #67 |
| Time to First Token | #498 |
| SciCode | #45 |
| LCR | #65 |
| TerminalBench Hard | #72 |
| TAU2 | #18 |
| Output TPS | #164 |
Capabilities
Input3/5
Text✓
Image✓
Audio·
Video✓
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Fast | Batch | |||||
|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.574 | $3.01 | N/A | — | — | — | — | $0.287 | $1.51 | |
| $0.6 | $3.00 | N/A | $0.3 | $1.50 | $1.05 | $5.25 | $0.3 | $1.50 | |
| $0.66 | $3.30 | $0.11 | — | — | — | — | — | — | |
| $0.6 | $3.00 | N/A | — | — | — | — | — | — | |
| $0.6 | $3.00 | N/A | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
| $0.45 | $2.25 | $0.07 | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
| $0.6 | $3.00 | N/A | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
| $0.45 | $2.25 | $0.07 | — | — | — | — | — | — | |
| $0.5 | $2.80 | N/A | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
| $0.6 | $3.00 | $0.1 | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Kimi K2.5, ranked by cheapest on-demand price. The model needs about 2541 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
No GPU instances fit Kimi K2.5 at FP16 precision — try a lower precision such as INT4.
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Kimi K2.7 Code | 262K | $0.660 | $3.40 | Deprecated | |
| Kimi K2.6 | 262K | $0.650 | $3.40 | Available | |
| Kimi K2.5 | 262K | $0.450 | $2.25 | Current |