Kimi K2.6 API pricing
Moonshot · Mid-range price tier · Modified MIT · released 2026-03. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $268.00 on Kimi K2.6; the next cheaper model in the Mid-range price tier for this workload, Kimi K2.7 Code, does it for $265.00. The price we quote for Kimi K2.6 has changed 9 times since 2026-08-15, most recently on 2026-10-11 when the quoted host changed (+39.2%); it is now the 39th cheapest of 113 models in the Mid-range price tier. Buying from Chutes rather than at the price we quote lowers the token price by about 47%, for a quantized int4 build. It holds the FinOps Friendly badge: top-40% Arena quality, top-30% Efficiency, not among the dearest 30%, and no stability flag.
- Input: $0.65 per 1M tokens
- Output: $3.41 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.15 per 1M tokens
- Context window: 262K tokens
- Arena ELO: 1455 as of 2026-11-08
Market position
On blended price ($2.582 per 1M tokens at 30% input, 70% output) it is cheaper than 66% of models in the Mid-range price tier: 39th cheapest of 113. Across every price tier it is cheaper than 34% of priced text models in the catalogue: 199th cheapest of 303. Its Arena ELO of 1455 ranks 32nd of the 160 models that carry one, above 81% of them. With an Arena score of 1455, Kimi K2.6 clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. It is 15 points under the Strong bar (Arena 1470+), within the benchmark's 20-point noise. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
Kimi K2.6 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, Vision, Reasoning, Agents. Filling its 262K context window once costs $0.1703 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 15 different hosts. 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.
Cheapest host: Chutes at $0.39 input / $1.80 output per 1M tokens, 47% below the price we quote on the blended price (30% input, 70% output). It serves a quantized int4 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $148.50 there against $268.00 at the price we quote, a difference of $119.50 a month. The dearest, Cloudflare, charges 2.2x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Chutes | $0.39 | $1.80 | int4 |
| DigitalOcean | $0.57 | $2.40 | not declared |
| StreamLake | $0.5985 | $2.52 | fp8 |
| Baidu | $0.6498 | $2.736 | fp4 |
| CoreWeave (price we quote) | $0.65 | $3.41 | fp4 |
| SiliconFlow | $0.77 | $3.40 | fp8 |
| Novita | $0.80 | $3.40 | not declared |
| Crusoe | $0.70 | $3.50 | bf16 |
| DeepInfra | $0.75 | $3.50 | fp4 |
| Venice | $0.75 | $3.50 | int4 |
| Parasail | $0.75 | $3.50 | int4 |
| Inceptron | $0.7995 | $3.75 | int4 |
| Moonshot AI (model maker) | $0.95 | $4.00 | not declared |
| AtlasCloud | $0.95 | $4.00 | int4 |
| Cloudflare | $0.95 | $4.00 | not declared |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest. These listings are promotional rates, below the host's standard rate: StreamLake's, 37% off; and Baidu's, 32% off.
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 | $223 – $268 |
| Knowledge Q&A | 2,000 / 800 | $333 – $403 |
| Meeting Summary | 10,000 / 1,200 | $1.0K – $1.1K |
| Marketing Content | 2,500 / 1,800 | $751 – $776 |
| Coding Task | 3,000 / 2,000 | $802 – $877 |
| Invoice Processing | 1,500 / 600 | $280 – $302 |
| Call Summary | 2,000 / 700 | $359 – $369 |
| Agent Workflow | 6,000 / 3,000 | $1.2K – $1.4K |
Price history
Kimi K2.6 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.5415 input / $2.28 output per 1M tokens. The price we quote has changed 9 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-11, was +39.2% on the blended price (30% input, 70% output), to $0.65 input / $3.41 output (quoted host changed, not a repricing). Net of all changes, the blended price is +46.8% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-11 | $0.465 / $2.45 | $0.65 / $3.41 | +39.2% (quoted host changed, not a repricing) |
| 2026-10-07 | $0.95 / $4.00 | $0.465 / $2.45 | -39.9% (quoted host changed, not a repricing) |
| 2026-10-04 | $0.4342 / $1.828 | $0.95 / $4.00 | +118.8% |
| 2026-10-02 | $0.65 / $3.41 | $0.4342 / $1.828 | -45.4% (quoted host changed, not a repricing) |
| 2026-09-28 | $0.95 / $4.00 | $0.65 / $3.41 | -16.3% (quoted host changed, not a repricing) |
4 earlier changes are not listed.
Alternatives to Kimi K2.6
1 of the 4 comparable models below costs less than Kimi K2.6: Grok 4.20 Multi-Agent undercuts it by 18%, for 4 Arena points less.
- Next cheaper model in the Mid-range price tier: GLM 5 (Zhipu) at $2.54 blended, 2% less.
- Next more expensive: Qwen3 235B A22B Thinking 2507 (Alibaba) at $2.585 blended, under 1% more.
The nearest models in the Mid-range price tier on Arena ELO, each with its blended price and score difference against Kimi K2.6.
- Gemini 2.5 Pro (Google): $1.25 in / $10.00 out per 1M, Arena ELO 1458 (186% more expensive, 3 ELO points higher)
- Grok 4.20 Multi-Agent (xAI): $1.25 in / $2.50 out per 1M, Arena ELO 1451 (18% cheaper, 4 ELO points lower)
- GPT-5.6 Terra (OpenAI): $2.00 in / $12.00 out per 1M, Arena ELO 1449 (249% more expensive, 6 ELO points lower)
- Grok 4.5 (xAI): $2.00 in / $6.00 out per 1M, Arena ELO 1448 (86% more expensive, 7 ELO points lower)
- Cheapest within 15 Arena points: MiMo-V2.6-Flash (Xiaomi), 91% cheaper, 4 ELO points lower, out of 31 models in that band.
- Highest Arena ELO within 20% of this price: Gemini 3.8 Flash (Google), 10% more expensive, 45 ELO points higher, out of 13 models in that price band.
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 Thinking: $0.60 / $2.50
- Kimi K2.5: $0.532 / $3.325
- 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 K2.6 pricing
- How much does Kimi K2.6 cost?
- Kimi K2.6 costs $0.65 per 1M input tokens and $3.41 per 1M output tokens at CoreWeave, the host whose rate we quote. CoreWeave serves a quantized fp4 build, which is not the same product as the full-precision model. The model maker, Moonshot AI, lists it at $0.95 per 1M input tokens and $4.00 per 1M output tokens. Prices as listed on 2026-11-12.
- Which host is cheapest for Kimi K2.6?
- Cheapest host: Chutes at $0.39 input / $1.80 output per 1M tokens, 47% below the price we quote on the blended price (30% input, 70% output). It serves a quantized int4 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $148.50 there against $268.00 at the price we quote, a difference of $119.50 a month. The dearest, Cloudflare, charges 2.2x the cheapest. Host rates as listed on 2026-11-12.
- Does Kimi K2.6 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 K2.6 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $268 on Kimi K2.6 at the list price quoted on 2026-11-12.
- Can Kimi K2.6 be self-hosted?
- Yes, within the terms of its licence. Kimi K2.6 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 K2.6 changed?
- Kimi K2.6 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.5415 input / $2.28 output per 1M tokens. The price we quote has changed 9 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-11, was +39.2% on the blended price (30% input, 70% output), to $0.65 input / $3.41 output (quoted host changed, not a repricing). Net of all changes, the blended price is +46.8% against 2026-08-15.
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