Automatic prefix caching
Eligible prior prompt prefixes must exceed 256 tokens. A cache hit maps to cached input in this dataset; it is not assumed for every input token.
Moonshot AI API Pricing
Moonshot AI rows provide current, source-linked Kimi API costs. Cache-miss tokens map to normal input, eligible automatic prefix-cache hits map to cached input, and billable reasoning tokens remain part of output usage.
- MODELS COVERED
- 5
- DATA SOURCE
- Official Moonshot AI
- PRICING UNIT
- Per 1M tokens
- LAST VERIFIED
- Oct 24, 2026
API cost estimate
Estimate Moonshot AI API Cost
Choose a current Moonshot AI model from the same pricing rows, enter input tokens, output tokens, and request volume, then review the estimated monthly API cost.
Moonshot AI cost planning
Estimate Moonshot AI API cost before monthly usage scales.
Start with realistic input tokens, output tokens, model choice, request volume, and any automatic prefix cache-hit pricing rules that apply. Then compare the estimate against current model pricing and budget limits before launch.
Kimi billing semantics
How Kimi cache hits and reasoning affect API cost.
Use the normal input rate for cache misses. The lower cache-hit rate applies only to eligible repeated prefixes handled by Moonshot AI's automatic prefix cache.
Reasoning output
K3 always reasons and K2.7 Code always thinks. K2.6 thinking is enabled by default and can be disabled. Reasoning tokens consume output-token quota and use the normal output price, without a separate surcharge.
Batch and tools
Verified Batch tiers are preserved only for K2.7 Code and K2.6. No per-model web-search fee is published here because the current official pages do not uniquely establish that charge for every listed model.
Dedicated model pages
Pricing by model
Open a model page for its verified source, workload examples, price history, lifecycle details, and nearby alternatives.
Current model pricing
Model costs per 1M tokens.
Null or unverified values are displayed as Not listed, never as zero.
| Model | Input | Output | Cached Input | Batch Input | Batch Output | Unit | Status |
|---|---|---|---|---|---|---|---|
Kimi K2.6Model ID: kimi-k2.6Provider: Moonshot AIDisplayed pricing: StandardEvidence Verified: Checked: Official sources (4): Official source 1Official source 2Official source 3Official source 4 | Input · USD per 1M input tokens$0.950 | Output · USD per 1M output tokens$4.00 | Cached input · USD per 1M cached input tokens$0.160 | Batch input · USD per 1M input tokens$0.570 | Batch output · USD per 1M output tokens$2.40 | USD per 1M tokens | latestStandard |
Kimi K2.7 CodeModel ID: kimi-k2.7-codeProvider: Moonshot AIDisplayed pricing: StandardEvidence Verified: Checked: Official sources (4): Official source 1Official source 2Official source 3Official source 4 | Input · USD per 1M input tokens$0.950 | Output · USD per 1M output tokens$4.00 | Cached input · USD per 1M cached input tokens$0.190 | Batch input · USD per 1M input tokens$0.570 | Batch output · USD per 1M output tokens$2.40 | USD per 1M tokens | latestStandard |
Kimi K3Model ID: kimi-k3Provider: Moonshot AIDisplayed pricing: StandardEvidence Verified: Checked: Official sources (4): Official source 1Official source 2Official source 3Official source 4 | Input · USD per 1M input tokens$3.00 | Output · USD per 1M output tokens$15.00 | Cached input · USD per 1M cached input tokens$0.300 | Batch input · USD per 1M input tokensNot listed | Batch output · USD per 1M output tokensNot listed | USD per 1M tokens | latestStandard |
Kimi K3.1 ProModel ID: kimi-k3.1-proProvider: Moonshot AIDisplayed pricing: StandardEvidence Verified: Checked: Official sources (4): Official source 1Official source 2Official source 3Official source 4 | Input · USD per 1M input tokens$2.00 | Output · USD per 1M output tokens$10.00 | Cached input · USD per 1M cached input tokens$0.200 | Batch input · USD per 1M input tokensNot listed | Batch output · USD per 1M output tokensNot listed | USD per 1M tokens | latestactive |
Kimi K3.1 Pro HighspeedModel ID: kimi-k3.1-pro-highspeedProvider: Moonshot AIDisplayed pricing: StandardEvidence Verified: Checked: Official sources (4): Official source 1Official source 2Official source 3Official source 4 | Input · USD per 1M input tokens$4.00 | Output · USD per 1M output tokens$20.00 | Cached input · USD per 1M cached input tokens$0.200 | Batch input · USD per 1M input tokensNot listed | Batch output · USD per 1M output tokensNot listed | USD per 1M tokens | latestactive |
Use these Moonshot AI pricing rows as planning inputs: calculate your monthly API cost with realistic token counts, or compare this provider with other AI models before routing production traffic.
Moonshot AI API pricing guide
What is Moonshot AI API pricing?
Moonshot AI API pricing is the usage-based cost of running Kimi models through API requests. The practical estimate depends on the selected model, input tokens, output tokens, monthly request volume, retries, and any listed caching or discount rules.
How to estimate Moonshot AI API cost
Estimate one representative request first: input tokens, expected output tokens, selected Kimi models, request volume, retry rate, and automatic prefix cache-hit pricing assumptions when they are listed. Then multiply by monthly traffic.
Open the Moonshot AI API cost calculatorMoonshot AI model pricing table
Use the table on this page to compare available Moonshot AI rows per 1M tokens. Not listed values stay visible as Not listed, so unknown prices are not accidentally treated as zero.
Compare Moonshot AI models
Compare total workflow cost, not only the cheapest input token price. Output length, quality, retries, context size, and fallback routing can change the real monthly API bill.
Compare Moonshot AI with other providersMoonshot AI model use cases
Which Moonshot AI models are usually used for.
Use cases are planning categories, not pricing promises. Estimate each workflow with its own token shape, expected answer length, quality requirement, and fallback behavior.
Long-context reasoning
Kimi K3 can be evaluated for research, document-heavy workflows, agent planning, and other tasks that need a large context window.
Coding agents
Kimi K2.7 Code is designed for software engineering and tool-driven coding workflows, with standard and high-speed serving prices kept as separate tiers.
Cost-aware model routing
Compare cache-miss input, eligible cache hits, billable reasoning output, retries, and Batch eligibility before routing production traffic.
Provider comparison
Moonshot AI pricing vs OpenAI, Claude, and Gemini.
Compare Moonshot AI with OpenAI, Claude, Gemini, and DeepSeek by input price, output price, cached-input behavior, context needs, latency, quality, and cost per successful task. Always verify current provider pricing before launch or procurement decisions.
Monthly spend control
How to control monthly Moonshot AI API spend.
Estimate before launch
Model a normal, high, and worst-case month with expected requests, input tokens, output tokens, retries, and model routes before exposing a feature to real traffic.
Set budget limits
Decide which app, workspace, customer tier, or internal team can spend against the provider budget. Review burn rate weekly during launches and pricing changes.
Reduce avoidable tokens
Shorten repeated instructions, cap output length, avoid sending full history when a summary works, and route routine tasks to lower-cost models when quality testing supports it.
Official sources
Source URLs used for this provider.
Cost examples
- 1M input tokens
- $0.950
- Model
- Kimi K2.6
- 1M output tokens
- $4.00
- Model
- Kimi K2.6
- 10M input + 2M output
- $17.50
- Model
- Kimi K2.6
Calculate a workload with Moonshot AI pricing context.
The existing calculator route is linked directly without invented provider or model query parameters.
Pricing data is informational and may lag provider changes. Always verify final billing decisions against provider pricing pages, contracts, dashboards, and invoices.
Moonshot AI API pricing FAQ
How much does the Moonshot AI API cost?
Moonshot AI API cost depends on the selected model, input tokens, output tokens, request volume, retries, and any automatic prefix cache-hit pricing or discount rules that apply. Use the pricing table and calculator with your own workload assumptions instead of relying on a single average price.
How do I estimate monthly Moonshot AI API cost?
Estimate one request with input tokens, expected output tokens, model choice, and current per-1M-token pricing. Then multiply by requests per user, active users, days per month, retry rate, and fallback calls.
Which Moonshot AI models are usually used for?
Kimi models are usually evaluated for workflows such as long-context reasoning, coding agents, cost-aware model routing. The best route depends on quality, latency, context size, output length, and monthly budget.
Is Moonshot AI cheaper than OpenAI, Claude, or Gemini?
Moonshot AI can be cheaper or more expensive depending on the exact model, prompt size, output length, cache eligibility, retry rate, and quality target. Compare total workflow cost across providers before switching production traffic.
Why are some Moonshot AI prices shown as Not listed?
Not listed means the current local pricing source does not expose a confirmed numeric value for that field. It is intentionally not treated as zero. Check the official Moonshot AI pricing page and billing dashboard before launch.
How can I control monthly Moonshot AI API spend?
Control spend by setting monthly budget limits, measuring input and output tokens separately, capping output length, reducing repeated context, reviewing retry cost, and comparing model routes before high-volume traffic grows.