Moonshot AI
Kimi K2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Cost / 1M tokens
Low usage$0.50
input
$0.15
cached input
$2.50
output
Context Window
262K
Up to 236K max output
Modalities
text, image → text
Other tokenizer
Quickstart & API
moonshotai/kimi-k2.5Best for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Coding agents
- Complex reasoning & debugging
- Screenshot-to-code workflows
Verified Evaluations
Benchmarks & Frontier Comparison
How Kimi K2.5 compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | Kimi K2.5 | DeepSeek V4.1 Flash | GLM 5.3 | Kimi K3.1 Pro | Claude Opus 5.5 |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | — | 63.2% | 58.3% | 65% | 74.1% |
| SWE-Bench Verified (%) | — | 91.5% | 95.4% | 94.8% | 97% |
| DeepSWE v1.1 (Pass@1 %) | — | 77% | 69% | 73.5% | 74.2% |
| Vibe Code Bench v1.1 (%) | — | 87.7% | 78.1% | 88.4% | 90.3% |
| Terminal-Bench 4.0 (%) | — | 42.3% | 42% | 46.2% | 65.2% |
| Code Migration (%) | — | 45.6% | 44.2% | 52% | 66.7% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 23.5 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.50 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $2.50 | $0.60 | $4.40 | $10.00 | $20.00 |
Artificial Analysis Intelligence Index
Artificial Analysis
Design Arena: ANDROIDNATIVE
Design Arena · Rank #27 (57.8% win)
Design Arena: FULLSTACK
Design Arena · Rank #28 (54.5% win)
Design Arena: GODOTGAMEDEV
Design Arena · Rank #15 (59.8% win)
Design Arena: MOBILEAPPS
Design Arena · Rank #30 (54.7% win)
Active Provider Endpoints (5)
Upstream inference providers serving Kimi K2.5, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
AtlasCloudcache atlas-cloud/int4 | $0.49 | $2.50 | $0.20 | 262K | 236K | int4 | 97.5% |
SiliconFlowcache siliconflow/int4 | $0.50 | $2.50 | $0.15 | 262K | 236K | int4 | 100.0% |
Venicecache venice | $0.532 | $3.33 | $0.209 | 256K | 66K | — | 99.9% |
Novitacache novita | $0.57 | $2.85 | $0.095 | 262K | 236K | — | 99.6% |
Amazon Bedrock amazon-bedrock/us-east-2 | $0.60 | $3.00 | — | 262K | 131K | — | 100.0% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Compare Similar Models
Browse all models →Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
Moonshot AI
Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Moonshot AI
Kimi K2.7 Code
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Moonshot AI
Kimi K2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Anthropic
Claude Opus 5
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...