Charm Hyper
Kimi K2 Thinking
kimi-k2-thinking
Prices and limits
- Input price per 1M tokens
- $0.60
- Output price per 1M tokens
- $2.50
- Cached input per 1M tokens
- $0.30
- Blended price per 1M (our estimate)
- $1.08
- Context window
- 262,144
- Max output tokens
- 26,214
- Accepts
- Text
- Produces
- Text
- Released
- Sep 2, 2026
- Last updated
- Sep 2, 2026
- Knowledge cutoff
- Aug 2024
- Open weights
- Yes
Wrong price, or a provider that wants its listing corrected or removed? Email ceo@uniholix.com. We reply within 5 business days.
Cheapest comparable models
Other priced models that accept at least the same inputs, produce the same outputs and have at least half this context window, sorted by blended price.
- GPT OSS 20B (Greenference)Eden AI$0.009 / $0.045131.1K
- DeepSeek V4.1 Flash (Greenference)Eden AI$0.0015 / $0.091M
- Llama-3.1-8B-InstructKilo Gateway$0.02 / $0.04131.1K
- Mistral Nemo Instruct 2407Meganova$0.02 / $0.04131.1K
- Ling 3.0 FlashVercel AI Gateway$0.021 / $0.063256K
- Llama 3.2 3b InstructNanoGPT$0.031 / $0.049131.1K
- qwen3.5-2bRequesty$0.02 / $0.10262.1K
- Mistral Nemo Instruct 2407 TEEChutes$0.025 / $0.098131.1K
Same model at other providers
Matched by the catalogue’s model ID. Cheapest blended price first.
- Kimi K2 ThinkingVercel AI Gateway$0.47 / $2.00216.1K
- Kimi K2 ThinkingIO.NET$0.55 / $2.2532.8K
- Kimi K2 ThinkingAmazon Bedrock$0.60 / $2.50262.1K
- Kimi K2 ThinkingKilo Gateway$0.60 / $2.50262.1K
- Kimi K2 ThinkingDevPass (LLM Gateway)$0.60 / $2.50262.1K
- Kimi K2 ThinkingNanoGPT$0.60 / $2.50262.1K
- Kimi K2 ThinkingNovitaAI$0.60 / $2.50262.1K
- Kimi K2 Thinking (Amazon Bedrock)Eden AI$0.60 / $2.50256K
- Kimi K2 Thinking (Vertex AI (OpenAI-compatible))LLM Gateway$0.60 / $2.50262.1K
- Kimi-K2-ThinkingHugging Face$0.60 / $2.50262.1K
- Kimi K2 ThinkingMeganova$0.60 / $2.60262.1K
- Kimi K2 ThinkingQiniu— / —256K
Price changes
Models whose price changed in the catalogue, newest first. We compare prices every day.
No price changes recorded yet. When a model’s price changes, it appears here.