Kimi K2.5 vs Kimi K2 Thinking
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
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.
- Reasoning estimated
- Speed estimated
- ▲
- Input
- Output
- Context
- 262 K tokens
- Max output
- ▲236 K
- Input, $ per 1M tokens
- ▲$0.450
- Output, $ per 1M tokens
- ▲$2.25
- Cache read, $ per 1M
- $0.070
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- ▲01/27/2026
- Knowledge cutoff
- 2025-01
- API id
- moonshotai/kimi-k2.5
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
- Reasoning estimated
- ▲
- Speed estimated
- Input
- Output
- Context
- 262 K tokens
- Max output
- 98 K
- Input, $ per 1M tokens
- $0.600
- Output, $ per 1M tokens
- $2.50
- Cache read, $ per 1M
- $0.150
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 11/06/2025
- Knowledge cutoff
- —
- API id
- moonshotai/kimi-k2-thinking
Which is the better API choice: Kimi K2.5 vs Kimi K2 Thinking?
- Kimi K2.5: cheapest input (25% less than Kimi K2 Thinking)
- Kimi K2.5: cheapest output
- Kimi K2.5: the newest (01/27/2026)
- Kimi K2 Thinking: most reasoning (estimated)
- Kimi K2.5: the fastest (estimated)
Kimi K2.5 costs 25% less on input and 10% less on output than Kimi K2 Thinking ($0.450 / $2.25 versus $0.600 / $2.50 per million tokens). All accept 262 K tokens of context. On capabilities, Kimi K2.5 accepts images.
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
With Kimi K2.5 you save $3.25 a month versus Kimi K2 Thinking (17% less).
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Paste your prompt: tokens and cost per model
Rough estimate (about 4 characters per token). Nothing is sent to any server.
Cost of sending it 1,000 times (input only)
- 1Kimi K2.5 Moonshot$0.034
- 2Kimi K2 Thinking Moonshot$0.046
- 3Claude Sonnet 5.5 Anthropic$0.152
- 4Claude Sonnet 5 Anthropic$0.152
- 5Claude Opus 5.5 Anthropic$0.304
- 6Claude Opus 5 Anthropic$0.380
- 7Claude Fable 5.1 Anthropic$0.760
- 8Claude Fable 5 Anthropic$0.760
Popular comparisons
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Sonnet 5.5 vs Gemini 3.8 Flash
- Claude Sonnet 5.5 vs DeepSeek V4.1 Flash
- Claude Sonnet 5.5 vs Grok 4.7
- GPT-6.1 Sol vs Gemini 3.8 Flash
- GPT-6.1 Sol vs DeepSeek V4.1 Flash
- GPT-6.1 Sol vs Grok 4.7
- Gemini 3.8 Flash vs DeepSeek V4.1 Flash
- Gemini 3.8 Flash vs Grok 4.7
- DeepSeek V4.1 Flash vs Grok 4.7
Frequently asked questions
Which is the better API choice: Kimi K2.5 vs Kimi K2 Thinking?
Kimi K2.5 costs 25% less on input and 10% less on output than Kimi K2 Thinking ($0.450 / $2.25 versus $0.600 / $2.50 per million tokens). All accept 262 K tokens of context. On capabilities, Kimi K2.5 accepts images.
Which is cheaper: Kimi K2.5 and Kimi K2 Thinking?
Kimi K2.5 is cheaper: $0.450 per million input tokens and $2.25 per million output tokens, versus $0.600 / $2.50 for Kimi K2 Thinking.
Which has more context: Kimi K2.5 and Kimi K2 Thinking?
Kimi K2.5 and Kimi K2 Thinking accept the same context: 262 K tokens.
Which is newer: Kimi K2.5 and Kimi K2 Thinking?
Kimi K2.5 was released on 01/27/2026; Kimi K2 Thinking on 11/06/2025.
What would 10,000 requests a month cost with Kimi K2.5 and Kimi K2 Thinking?
With 1,500 input and 400 output tokens per request: Kimi K2.5: $15.75; Kimi K2 Thinking: $19.00 a month, at list price.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.