Kimi K2 Models by Moonshot AI
8 models2025–2026Up to 262K ctxFrom $0.5/1M input
About
Kimi K2 is Moonshot AI's frontier MoE model family for agentic coding and long-context reasoning. The line spans the original K2 release and Kimi K2.6, with 1T total parameters, 32B active parameters, a 262K-token context window, and support for coding, tool use, and vision-assisted workflows.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
8 in view
Kimi K2.6Current
Use when the workload needs code, 262K context, and 1000B parameters.
2026-04code262K context1000B parameters
Kimi K2 0905 PreviewCurrent
Use when the workload needs 262K context, 1K parameters, and function calling.
2025-09262K context1K parametersfunction calling
Kimi K2 Turbo PreviewCurrent
Use when the workload needs 262K context, 1K parameters, and function calling.
2025-08262K context1K parametersfunction calling
Kimi K2Current
Use when the workload needs 262K context, 1K parameters, and function calling.
2025-07262K context1K parametersfunction calling
Kimi K2 0711 PreviewCurrent
Use when the workload needs 131K context, 1K parameters, and function calling.
2025-07131K context1K parametersfunction calling
Kimi K2 ThinkingCurrent
Use when the workload needs reasoning, 256K context, and structured outputs.
2025-01reasoning256K contextstructured outputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Kimi K2.6 | Use when the workload needs code, 262K context, and 1000B parameters. | 2026-04 | code262K context1000B parameters | Current |
| Kimi K2 Thinking Turbo | Use when the workload needs 262K context. | 2025-11 | 262K context | Current |
| Kimi K2 0905 Preview | Use when the workload needs 262K context, 1K parameters, and function calling. | 2025-09 | 262K context1K parametersfunction calling | Current |
| Kimi K2 Turbo Preview | Use when the workload needs 262K context, 1K parameters, and function calling. | 2025-08 | 262K context1K parametersfunction calling | Current |
| Kimi K2 | Use when the workload needs 262K context, 1K parameters, and function calling. | 2025-07 | 262K context1K parametersfunction calling | Current |
| Kimi K2 0711 Preview | Use when the workload needs 131K context, 1K parameters, and function calling. | 2025-07 | 131K context1K parametersfunction calling | Current |
| Kimi K2 Instruct 0905 | Use when the workload needs 256K context. | 2025-01 | 256K context | Current |
| Kimi K2 Thinking | Use when the workload needs reasoning, 256K context, and structured outputs. | 2025-01 | reasoning256K contextstructured outputs | Current |
Release Timeline
6 release groups2026-04
1 current
Kimi K2.6
Currentcode262K context1000B parameters
2025-11
1 current
Kimi K2 Thinking Turbo
Current262K context
2025-09
1 current
Kimi K2 0905 Preview
Current262K context1K parametersfunction calling
2025-08
1 current
Kimi K2 Turbo Preview
Current262K context1K parametersfunction calling
2025-07
2 current
Kimi K2
Current262K context1K parametersfunction calling
Kimi K2 0711 Preview
Current131K context1K parametersfunction calling
2025-01
2 current
Kimi K2 Instruct 0905
Current256K context
Kimi K2 Thinking
Currentreasoning256K contextstructured outputs
Specifications(8 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|---|---|---|
| Kimi K2.6 | 2026-04 | 262K | 1T | Yes | Yes | Yes | Yes | Yes | No |
| Kimi K2 Thinking Turbo | 2025-11 | 262K | — | No | No | No | No | No | No |
| Kimi K2 0905 Preview | 2025-09 | 262K | 1K | No | No | No | Yes | No | No |
| Kimi K2 Turbo Preview | 2025-08 | 262K | 1K | No | No | No | Yes | No | No |
| Kimi K2 | 2025-07 | 262K | 1K | No | No | No | Yes | No | Yes |
| Kimi K2 0711 Preview | 2025-07 | 131K | 1K | No | No | No | Yes | No | No |
| Kimi K2 Instruct 0905 | 2025-01 | 256K | — | No | No | No | No | No | No |
| Kimi K2 Thinking | 2025-01 | 256K | — | No | No | Yes | No | No | Yes |
Available From(7 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Kimi K2 | AWS Bedrock | $0.5 | $2 | Serverless |
| Kimi K2 | GCP Vertex AI | $0.5 | $2 | Serverless |
| Kimi K2 | OpenRouter | $0.57 | $2.3 | Serverless |
| Kimi K2 Instruct 0905 | Fireworks AI | $0.6 | $2.5 | Serverless |
| Kimi K2 Thinking | Fireworks AI | $0.6 | $2.5 | Serverless |
| Kimi K2 Thinking | GCP Vertex AI | $0.6 | $2.5 | Serverless |
| Kimi K2 Thinking | AWS Bedrock | $0.6 | $2.5 | Serverless |
| Kimi K2 Thinking | OpenRouter | $0.6 | $2.5 | Serverless |
| Kimi K2.6 | OpenRouter | $0.75 | $3.5 | Serverless |
| Kimi K2.6 | Moonshot AI Kimi | $0.9 | $3.72 | Serverless |
| Kimi K2.6 | Fireworks AI | $0.95 | $4 | Serverless |
Comparisons
- DeepSeek V4 Flash vs Kimi K2.6
- Claude Opus 4.7 vs Kimi K2 Thinking
- Kimi K2.6 vs Kimi K2.5
- Kimi K2.6 vs Claude Opus 4.7
- Kimi K2.6 vs DeepSeek V4 Pro
- Kimi K2.6 vs GPT-5.2 Codex
- Kimi K2.6 vs GPT-5.1 Codex Max
- Kimi K2.6 vs GPT-5.5
Frequently Asked Questions
- What is Kimi K2 used for?
- Kimi K2 is used for code, reasoning, and vision and multimodal work. The family description and listed model capabilities point to those workloads as the best fit.
- How does Kimi K2 compare to Moonshot?
- Kimi K2 by Moonshot AI is strongest where you need code, while Moonshot by Moonshot AI is the closest related family to check for adjacent model selection. Kimi K2 has 8 listed variants and reaches up to 262K context, while Moonshot reaches up to 128K context, so compare the specs and pricing tables before choosing a production model.
Models(8)
Kimi K2.6
2026-04262K1T5 providers
MultimodalReasoningOpen Source
Kimi K2 Thinking Turbo
2025-11262K
Kimi K2 0905 Preview
2025-09262K1K
Kimi K2 Turbo Preview
2025-08262K1K
Kimi K2
2025-07262K1K3 providers
Kimi K2 0711 Preview
2025-07131K1K
Kimi K2 Instruct 0905
2025-01256K2 providers
Kimi K2 Thinking
2025-01256K5 providers
Reasoning