Kimi K2 Thinking API pricing
Moonshot · Mid-range price tier · Modified MIT · released 2025-11. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $215.00 on Kimi K2 Thinking; the next cheaper model in the Mid-range price tier for this workload, Mistral Large 4, does it for $210.00. Kimi K2 Thinking has held the same list price since 2026-08-15 and is the 25th cheapest of 113 models in the Mid-range price tier. Only one host, Novita, sells it, so there is no second price to shop. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.60 per 1M tokens
- Output: $2.50 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.15 per 1M tokens
- Context window: 262K tokens
- Arena ELO: Not published
Available on
AWS Bedrock regions: ap-northeast-1, us-east-1, us-east-2, us-west-2
Market position
On blended price ($1.93 per 1M tokens at 30% input, 70% output) it is cheaper than 78% of models in the Mid-range price tier: 25th cheapest of 113, tied with one other. Across every price tier it is cheaper than 39% of priced text models in the catalogue: 185th cheapest of 303, tied with one other. No Arena score has been published for Kimi K2 Thinking, so this page does not rank it on quality and OptimNow's quality bars do not apply to it. 66 of the 113 models we list in the Mid-range price tier carry one. An unranked model is unmeasured, not poor: the benchmark needs votes, and a recent release has not had time to collect them.
Licence, size and capabilities
Kimi K2 Thinking is open weights, which is not the same as open source: the weights are published, but under Modified MIT, a licence that restricts some uses. Read it before self-hosting commercially. Its parameter count is not published. Listed capabilities: Text, Reasoning, Agents. Filling its 262K context window once costs $0.1572 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Novita is the only host with a published rate, $0.60 input / $2.50 output per 1M tokens, which is the price we quote.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Novita (price we quote) | $0.60 | $2.50 | bf16 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Moonshot publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $175 – $215 |
| Knowledge Q&A | 2,000 / 800 | $257 – $320 |
| Meeting Summary | 10,000 / 1,200 | $855 – $900 |
| Marketing Content | 2,500 / 1,800 | $578 – $600 |
| Coding Task | 3,000 / 2,000 | $613 – $680 |
| Invoice Processing | 1,500 / 600 | $220 – $240 |
| Call Summary | 2,000 / 700 | $286 – $295 |
| Agent Workflow | 6,000 / 3,000 | $921 – $1.1K |
Price history
Kimi K2 Thinking has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.60 input / $2.50 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.
Alternatives to Kimi K2 Thinking
Kimi K2 Thinking carries no Arena score, so this page cannot place it against models of comparable quality. The alternatives below are its nearest neighbours on price in the Mid-range price tier.
- Next cheaper model in the Mid-range price tier: Seed 2.1 Turbo (ByteDance) at $1.90 blended, 2% less.
- Next more expensive: Grok 4.20 (xAI) at $2.125 blended, 10% more.
Other models from Moonshot
Moonshot has 7 other models in the catalogue. Prices per 1M tokens, input then output.
- Kimi K2 0711: $0.57 / $2.30
- Kimi K2 0905: $0.60 / $2.50
- Kimi K2.5: $0.532 / $3.325
- Kimi K2.6: $0.65 / $3.41
- Kimi K2.7 Code: $0.60 / $3.50
- Kimi K3.1 Pro: $0.2375 / $8.4085
- Kimi K3: $0.192 / $16.00
All 8 Moonshot models and prices
Common questions about Kimi K2 Thinking pricing
- How much does Kimi K2 Thinking cost?
- Kimi K2 Thinking costs $0.60 per 1M input tokens and $2.50 per 1M output tokens at Novita, the host whose rate we quote. Prices as listed on 2026-11-12.
- Which host is cheapest for Kimi K2 Thinking?
- Novita is the only host with a published rate, $0.60 input / $2.50 output per 1M tokens, which is the price we quote. Host rates as listed on 2026-11-12.
- Does Kimi K2 Thinking offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.15 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would Kimi K2 Thinking cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $215 on Kimi K2 Thinking at the list price quoted on 2026-11-12.
- Can Kimi K2 Thinking be self-hosted?
- Yes, within the terms of its licence. Kimi K2 Thinking is open weights, which is not the same as open source: the weights are published, but under Modified MIT, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Kimi K2 Thinking changed?
- Kimi K2 Thinking has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.60 input / $2.50 output per 1M tokens. No list price change since tracking began on 2026-08-15. Last checked against the 2026-11-12 snapshot.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server