Kimi K2 Thinking
moonshotai/kimi-k2-thinkingPor Moonshot AI · família: kimi-thinking · lançado 2025-11-06 · data de conhecimento: 2024-08
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacidades
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding88
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)8/20
- Provider availability10/10
Agents95
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit10/15
- Provider availability10/10
JSON / structured output95
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume15/20
Cost efficiency58
- Headline price (log-scaled)53/95
- Has prompt-cache pricing5/5
Long context61
- Context window (100K → 2M)51/90
- Has published price for full window10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $3.35 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $6.70 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.94 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $5.76 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $6.84 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Detalhes de preço
Preço recomendado de vercel · moonshotai/kimi-k2-thinking
Disponível em 20 provedores
| Provedor | ID do modelo do provedor | Entrada / 1M | Saída / 1M | Contexto | Lançado |
|---|---|---|---|---|---|
| Amazon Bedrock amazon-bedrock | moonshot.kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| OpenRouter openrouter | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| Vercel AI Gateway vercel | moonshotai/kimi-k2-thinking | $0.470 | $2.00 | 216K | 2025-11-06 |
| Hugging Face huggingface | moonshotai/Kimi-K2-Thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| NanoGPT nano-gpt | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| LLM Gateway llmgateway-providers | vertex-openai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| Kilo Gateway kilo | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| NovitaAI novita-ai | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-07 |
| 302.AI 302ai | kimi-k2-thinking | $0.575 | $2.30 | 262K | 2025-09-05 |
| ZenMux zenmux | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| Qiniu qiniu-ai | moonshotai/kimi-k2-thinking | Unknown | Unknown | 256K | 2025-11-07 |
| Charm Hyper hyper | kimi-k2-thinking | $0.600 | $2.50 | 262K | 2026-09-02 |
| Merge Gateway merge-gateway | moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| Eden AI edenai | amazon/moonshot.kimi-k2-thinking | $0.600 | $2.50 | 256K | 2025-11-06 |
| OpenCode Zen opencode | kimi-k2-thinking | $0.400 | $2.50 | 262K | 2025-09-05 |
| Meganova meganova | moonshotai/Kimi-K2-Thinking | $0.600 | $2.60 | 262K | 2025-11-06 |
| DevPass (LLM Gateway) llmgateway | kimi-k2-thinking | $0.600 | $2.50 | 262K | 2025-11-06 |
| Helicone helicone | kimi-k2-thinking | $0.480 | $2.00 | 256K | 2025-11-06 |
| IO.NET io-net | moonshotai/Kimi-K2-Thinking | $0.550 | $2.25 | 33K | 2024-11-01 |
| Alibaba (China) alibaba-cn | kimi-k2-thinking | $0.574 | $2.29 | 262K | 2025-11-06 |
Inconsistências de dados entre provedores
- context_window varies: 216144, 256000, 262000, 262144, 32768
- release_date varies (span 670d): 2024-11-01, 2025-09-05, 2025-11-06, 2025-11-07, 2026-09-02
Os provedores reportam valores diferentes para este modelo. Os dados rápidos acima usam um provedor representativo; consulte a tabela para detalhes por provedor.
Frequently asked questions
How much does Kimi K2 Thinking cost?
Kimi K2 Thinking costs $0.470 per 1M input tokens and $2.00 per 1M output tokens, sourced from vercel. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Kimi K2 Thinking?
Kimi K2 Thinking has a context window of 262K tokens, with a max output of 16K tokens per reply. This is the total combined size of prompt + completion.
Does Kimi K2 Thinking support tool calling?
Yes. Kimi K2 Thinking supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Kimi K2 Thinking support structured output / JSON mode?
Yes. Kimi K2 Thinking supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Kimi K2 Thinking accept image input?
No. Kimi K2 Thinking only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Kimi K2 Thinking open-weight?
Yes. Kimi K2 Thinking's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Kimi K2 Thinking?
If Kimi K2 Thinking doesn't fit, consider Kimi K3, Kimi K2.6, Kimi K2.7 Code. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
Direct comparisons
More Moonshot AI models
- Kimi K3$3.00 in / $15.00 out
- Kimi K2.6$0.95 in / $4.00 out
- Kimi K2.7 Code$0.95 in / $4.00 out
- Kimi K2.5$0.30 in / $1.90 out
- Kimi K2.7 Code HighSpeed$1.90 in / $8.00 out
Capability lists this model is in
Última atualização:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.