Kimi K2.6 API Pricing
Moonshot · Mid-tier · Modified MIT · released 2026-03. Prices in USD per 1 million tokens. Data snapshot: 2026-09-06.
- Input: $0.95 per 1M tokens
- Output: $4.00 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.16
- Context window: 262K
- Arena ELO: 1461 (as of 2026-09-01)
Cost per request by business use case
List price vs optimized (prompt caching on the cached input share, batch API for async workloads, only where the provider publishes those rates).
| Use case | Tokens (in/out) | Cost/req (list) | Cost/req (optimized) | Monthly @100K req |
|---|---|---|---|---|
| Support Ticket | 1,500 / 500 | $0.0034 | $0.0027 | $271 |
| Knowledge Q&A | 2,000 / 800 | $0.0051 | $0.0040 | $399 |
| Meeting Summary | 10,000 / 1,200 | $0.014 | $0.014 | $1.4K |
| Marketing Content | 2,500 / 1,800 | $0.0096 | $0.0092 | $918 |
| Coding Task | 3,000 / 2,000 | $0.011 | $0.0097 | $967 |
| Invoice Processing | 1,500 / 600 | $0.0038 | $0.0035 | $347 |
| Call Summary | 2,000 / 700 | $0.0047 | $0.0045 | $454 |
| Agent Workflow | 6,000 / 3,000 | $0.018 | $0.014 | $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 20 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 2026-09-06 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.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Baidu — fp4 | $0.54 | $2.26 |
| Decart — fp4 | $0.54 | $2.26 |
| StreamLake — fp8 | $0.60 | $2.52 |
| Inceptron — int4 | $0.56 | $3.39 |
| Chutes — int4 | $0.58 | $3.40 |
| CoreWeave — 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 |
| DigitalOcean (the price shown above) | $0.95 | $4.00 |
| AtlasCloud (the price shown above) — int4 | $0.95 | $4.00 |
| Cloudflare (the price shown above) | $0.95 | $4.00 |
| Moonshot AI (the price shown above) — int4 | $0.95 | $4.00 |
| BaseTen (the price shown above) — fp4 | $0.95 | $4.00 |
| Fireworks (the price shown above) | $0.95 | $4.00 |
| Phala | $1.09 | $4.60 |
Models comparable to Kimi K2.6
The nearest Mid-tier models on Arena ELO, so a substitution is compared on quality as well as price.
- Grok 4.6 (xAI) — $2.00 in / $6.00 out per 1M, Arena ELO 1461
- Claude Sonnet 5 (Anthropic) — $2.00 in / $10.00 out per 1M, Arena ELO 1461
- Gemini 3.5 Flash Lite (Google) — $0.30 in / $2.50 out per 1M, Arena ELO 1458
- GPT-5.6 Terra (OpenAI) — $2.00 in / $12.00 out per 1M, Arena ELO 1466
Common questions about Kimi K2.6 pricing
- How much does Kimi K2.6 cost?
- Kimi K2.6 costs $0.95 per million input tokens and $4.00 per million output tokens on the API.
- Does Kimi K2.6 offer batch or cached pricing?
- Prompt-cache reads cost $0.16/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 $343 at list prices.
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