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...
Cost / 1M tokens
Medium usage$0.65
input
$0.15
cached input
$3.41
output
Context Window
262K
Up to 236K max output
Modalities
text, image → text
Other tokenizer
Quickstart & API
moonshotai/kimi-k2.6Best for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Coding agents
- Complex reasoning & debugging
- Screenshot-to-code workflows
Verified Evaluations
Benchmarks & Frontier Comparison
How Kimi K2.6 compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | Kimi K2.6 | 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) | 27 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.65 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $3.41 | $0.60 | $4.40 | $10.00 | $20.00 |
Artificial Analysis Intelligence Index
Artificial Analysis
Design Arena: AGENTICGAMEDEV
Design Arena · Rank #20 (47.5% win)
Design Arena: AGENTICHTMLSLIDES
Design Arena · Rank #2 (59% win)
Design Arena: AGENTICSLIDES
Design Arena · Rank #4 (45.8% win)
Design Arena: AGENTICSLIDES(HTML)
Design Arena · Rank #2 (59.2% win)
Active Provider Endpoints (17)
Upstream inference providers serving Kimi K2.6, 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) |
|---|---|---|---|---|---|---|---|
Baiducache baidu/fp4 | $0.39 | $1.64 | $0.066 | 262K | 236K | fp4 | 99.8% |
Chutescache chutes/int4 | $0.39 | $1.80 | $0.039 | 262K | 66K | int4 | 99.9% |
DigitalOceancache digitalocean | $0.57 | $2.40 | $0.114 | 262K | 236K | — | 100.0% |
Inceptroncache inceptron/int4 | $0.585 | $3.50 | $0.157 | 262K | 236K | int4 | 100.0% |
StreamLakecache streamlake/fp8 | $0.599 | $2.52 | $0.101 | 256K | 230K | fp8 | 95.4% |
CoreWeavecache coreweave/fp4 | $0.65 | $3.41 | $0.15 | 262K | 236K | fp4 | 99.4% |
Crusoecache crusoe/bf16 | $0.70 | $3.50 | $0.35 | 262K | 236K | bf16 | 98.9% |
DeepInfracache deepinfra/fp4 | $0.75 | $3.50 | $0.15 | 262K | 16K | fp4 | 99.8% |
Venicecache venice/int4 | $0.75 | $3.50 | $0.16 | 256K | 66K | int4 | 98.9% |
Parasailcache parasail/int4 | $0.75 | $3.50 | $0.16 | 262K | 236K | int4 | 100.0% |
SiliconFlowcache siliconflow/fp8 | $0.77 | $3.40 | $0.14 | 262K | 236K | fp8 | 100.0% |
Novitacache novita | $0.80 | $3.40 | $0.16 | 262K | 236K | — | 100.0% |
GMICloudcache gmicloud/fp8 | $0.855 | $3.60 | $0.144 | 262K | 236K | fp8 | 0.0% |
AtlasCloudcache atlas-cloud/int4 | $0.95 | $4.00 | $0.16 | 262K | 236K | int4 | 100.0% |
Cloudflarecache cloudflare | $0.95 | $4.00 | $0.16 | 262K | 236K | — | 100.0% |
Moonshot AIcache moonshotai | $0.95 | $4.00 | $0.16 | 262K | 236K | — | 96.9% |
Phalacache phala | $1.09 | $4.60 | $0.37 | 262K | 236K | — | 97.3% |
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 K2.5
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...
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...