Kimi K2.6 API Pricing
Moonshot · Mid-tier · Modified MIT · released 2026-03. Prices in USD per 1 million tokens. Data snapshot: 2026-09-28.
The price we publish for Kimi K2.6 has changed 5 times since 2026-08-15, most recently on 2026-09-28 when the reference host changed (-16.3%); it is now the 43rd cheapest of 108 Mid-tier models. Buying from Baidu rather than at the rate quoted here lowers the token price by about 40%, for a quantized fp4 build. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.65 per 1M tokens
- Output: $3.41 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.15
- Context window: 262K
- Arena ELO: 1461 (as of 2026-09-25)
Kimi K2.6 market position
On blended price ($2.58 per 1M tokens at 30% input, 70% output) it is cheaper than 61% of Mid-tier models: 43rd cheapest of 108. Across every category it is cheaper than 34% of priced text models in the catalogue: 185th cheapest of 281. Its Arena ELO of 1461 ranks 25th of the 68 models that carry one, above 64% of them.
Kimi K2.6 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, Code, Agents. Filling its 262K context window once costs $0.17 in input tokens at list price.
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 the provider 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 |
Kimi K2.6 pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 18 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-28 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.
Cheapest host: Baidu at $0.47 input / $2.00 output per 1M tokens, 40% below the price we publish on a blended basis (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. The dearest, Phala, charges 2.3x the cheapest.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Baidu — fp4 | $0.47 | $2.00 |
| Inceptron — int4 | $0.46 | $2.39 |
| DigitalOcean | $0.57 | $2.40 |
| Decart — fp4 | $0.59 | $2.47 |
| StreamLake — fp8 | $0.60 | $2.52 |
| Chutes — int4 | $0.50 | $2.85 |
| CoreWeave (the price shown above) — fp4 | $0.65 | $3.41 |
| SiliconFlow — fp8 | $0.77 | $3.40 |
| Novita | $0.80 | $3.40 |
| Crusoe — bf16 | $0.70 | $3.50 |
| DeepInfra — fp4 | $0.75 | $3.50 |
| Venice — int4 | $0.75 | $3.50 |
| Parasail — int4 | $0.75 | $3.50 |
| GMICloud — fp8 | $0.85 | $3.60 |
| AtlasCloud — int4 | $0.95 | $4.00 |
| Cloudflare | $0.95 | $4.00 |
| Moonshot AI — int4 | $0.95 | $4.00 |
| Phala | $1.09 | $4.60 |
Kimi K2.6 price history
Kimi K2.6 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.54 input / $2.28 output per 1M tokens. The price we publish has changed 5 times since then, 1 of them a change of reference host rather than a repricing. The latest change, on 2026-09-28, was -16.3% on the blended price (30% input, 70% output), to $0.65 input / $3.41 output (reference 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 |
|---|---|---|---|
| 2026-09-28 | $0.95 / $4.00 | $0.65 / $3.41 | -16.3% (reference host changed, not a repricing) |
| 2026-08-23 | $0.54 / $2.28 | $0.95 / $4.00 | +75.4% |
| 2026-08-22 | $0.95 / $4.00 | $0.54 / $2.28 | -43.0% |
| 2026-08-17 | $0.65 / $3.41 | $0.95 / $4.00 | +19.5% |
| 2026-08-16 | $0.54 / $2.28 | $0.65 / $3.41 | +46.8% |
Alternatives to Kimi K2.6
- Next cheaper Mid-tier model: Kimi K2.7 Code (Moonshot) at $2.51 blended, 3% less.
- Next more expensive: Qwen3.5 397B A17B (Alibaba) at $2.61 blended, 1% more.
The nearest Mid-tier models on Arena ELO, each with its blended price and score difference against Kimi K2.6.
- Claude Sonnet 5 (Anthropic) — $2.00 in / $10.00 out per 1M, Arena ELO 1462: 194% more expensive, 1 ELO point higher
- GPT-5.6 Terra (OpenAI) — $2.00 in / $12.00 out per 1M, Arena ELO 1465: 249% more expensive, 4 ELO points higher
- Grok 4.5 (xAI) — $2.00 in / $6.00 out per 1M, Arena ELO 1465: 86% more expensive, 4 ELO points higher
- GLM 5.1 (Zhipu) — $0.96 in / $3.03 out per 1M, Arena ELO 1465: 7% cheaper, 4 ELO points higher
- Cheapest within 15 Arena points: GLM 5.3 Flash (Zhipu), 85% cheaper, 13 ELO points higher, out of 22 models in that band.
- Highest Arena ELO within 20% of this price: Gemini 3.7 Flash (Google), 10% more expensive, 27 ELO points higher, out of 8 models in that price band.
Common questions about Kimi K2.6 pricing
- How much does Kimi K2.6 cost?
- Kimi K2.6 costs $0.65 per million input tokens and $3.41 per million output tokens on the API.
- Does Kimi K2.6 offer batch or cached pricing?
- Prompt-cache reads cost $0.15/M input tokens. No batch pricing is published.
- What would Kimi K2.6 cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Kimi K2.6 costs about $268 at list prices.
- 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 $0.54 input / $2.28 output per 1M tokens. The price we publish has changed 5 times since then, 1 of them a change of reference host rather than a repricing. The latest change, on 2026-09-28, was -16.3% on the blended price (30% input, 70% output), to $0.65 input / $3.41 output (reference host changed, not a repricing). Net of all changes, the blended price is +46.8% against 2026-08-15.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for Kimi K2.6 in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server