Kimi K2.6 API pricing
Updated
Among the 13 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Kimi K2.6 is Chutes at USD 0.39 per 1M input tokens and USD 1.80 per 1M output tokens. The median across 13 standard prices is USD 0.80 / USD 3.50. Moonshot AI's own API charges USD 0.95 / USD 4.
What does Moonshot AI charge for Kimi K2.6?
- Input
- USD 0.95
- Cached input
- USD 0.16
- Output
- USD 4
- Blended 3:1
- USD 1.712
USD per 1M tokens on Moonshot AI (Kimi), model kimi-k2.6, standard tier. Source, checked 2026-11-14.
Other Moonshot AI tiers: batch USD 0.57 / USD 2.40.
Is a host cheaper than Moonshot AI? Yes. Chutes charges USD 0.39 input and USD 1.80 output per 1M tokens, 57% below Moonshot AI's own USD 0.95 / USD 4 on the 3:1 blend.
Kimi K2.6 model facts
Facts from Moonshot AI's model card for moonshotai/Kimi-K2.6 and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (moonshotai/Kimi-K2.6) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 64 .safetensors files listed” |
| Licence | Modified MIT License | Moonshot AI model card, checked 2026-11-16Quote“Both the code repository and the model weights are released under the Modified MIT License.” |
| Total parameters | 1T | Moonshot AI model card, checked 2026-11-16Quote“Total Parameters | 1T” |
| Active parameters per token | 32B | Moonshot AI model card, checked 2026-11-16Quote“Activated Parameters | 32B” |
| Context length | 256K | Moonshot AI model card, checked 2026-11-16Quote“Context Length | 256K” |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | Moonshot AI model card metadata, checked 2026-11-16Quote“pipeline_tag: image-text-to-text” |
| Tool calling | Yes | Moonshot AI model card, checked 2026-11-16Quote“K2.6 shares the same design of Interleaved Thinking and Multi-Step Tool Call as K2 Thinking.” |
| First published on Hugging Face (not necessarily the release date) | 2026-04-14 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-04-14T04:23:36.000Z"” |
Kimi K2.6 price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.5× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Chutes cheapestmoonshotai/Kimi-K2.6-TEENotes and source quoteRuns on confidential TEE compute. “Kimi K2.6 moonshotai/Kimi-K2.6-TEE $0.039 per 1M tokens $0.39 per 1M tokens $1.80 per 1M tokens 262K” | USD 0.39 | USD 0.039 | USD 1.80 | USD 0.7425 | 262,144 | INT4 | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | CoreWeave Forgemoonshotai/Kimi-K2.6Notes and source quote“Moonshot AI Kimi K2.6 $0.65 $3.41 $0.15” | USD 0.65 | USD 0.15 | USD 3.41 | USD 1.34 | 262,144 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | SiliconFlowNotes and source quoteContext shown as 262K. “Kimi-K2.6 262K $0.77 $0.14 $3.4” | USD 0.77 | USD 0.14 | USD 3.40 | USD 1.427 | 262,144 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | DeepInframoonshotai/Kimi-K2.6Notes and source quote“$0.75 in $3.50 out $0.15 cached / 1M tokens” | USD 0.75 | USD 0.15 | USD 3.50 | USD 1.438 | 262,144 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | ParasailNotes and source quote“Kimi K2.6 $0.75 $3.50 $0.16” | USD 0.75 | USD 0.16 | USD 3.50 | USD 1.438 | not stated | not stated | Parasail page checked 2026-11-14 re-checked 2026-11-16 |
| 6 | Venicekimi-k2-6Notes and source quote“| Kimi K2.6 | `kimi-k2-6` | $0.75 | $3.50 | $0.16 | — | Private |” | USD 0.75 | USD 0.16 | USD 3.50 | USD 1.438 | 256,000 | INT4 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 7 | Featherlessmoonshotai/Kimi-K2.6Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.8 / CACHED $0.154 / OUTPUT $3.4” | USD 0.80 | USD 0.154 | USD 3.40 | USD 1.45 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 8 | Novita AImoonshotai/kimi-k2.6Notes and source quote“Kimi K2.6 256K $0.8 /Mt · Cache Read $0.16 /Mt $3.4 /Mt” | USD 0.80 | USD 0.16 | USD 3.40 | USD 1.45 | 262,144 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 9 | Moonshot AI makerkimi-k2.6Notes and source quoteMoonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026. “kimi-k2.6 | $0.95 / MTok | $4.00 / MTok | $0.16 / MTok” | USD 0.95 | USD 0.16 | USD 4 | USD 1.712 | 262,144 | not stated | Moonshot AI page checked 2026-11-14 re-checked 2026-11-16 |
| 10 | Baidukimi-k2.6Notes and source quote“Kimi-K2.6 Kimi-K2.6 Inference Service Input 0.95 $/M tokens Cache Hit 0.16 $/M tokens Output 4 $/M tokens” | USD 0.95 | USD 0.16 | USD 4 | USD 1.712 | 262,144 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| 11 | Cloudflare Workers AI@cf/moonshotai/kimi-k2.6Notes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/moonshotai/kimi-k2.6 $0.950 per M input tokens $0.160 per M cached input tokens $4.000 per M output tokens” | USD 0.95 | USD 0.16 | USD 4 | USD 1.712 | not stated | not stated | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 12 | DigitalOceanNotes and source quoteDigitalOcean-hosted. “Kimi K2.6 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.95$4.00$0.19” | USD 0.95 | USD 0.19 | USD 4 | USD 1.712 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 13 | Microsoft AzureNotes and source quoteFoundry Models serverless, served by Fireworks on Azure, Data Zone deployment. Also sold as "FW Kimi K2.6" (Fireworks on Azure, Data Zone): input $1.045, cached $0.176, output $4.40. “FW Kimi K2.6 Data Zone Input: $1.045/1M Tokens | Cached Input: $0.176/1M Tokens | Output: $4.40/1M Tokens” | USD 1.045 | USD 0.176 | USD 4.40 | USD 1.884 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| — | Moonshot AI maker batchkimi-k2.6Notes and source quoteBatch API, billed at 60% of the standard price. Moonshot says K2 series models are closed to newly registered users from October 31, 2026 and will be retired by the end of December 2026. “kimi-k2.6 | $0.57 / MTok | $2.40 / MTok | $0.10 / MTok | — | —” | USD 0.57 | USD 0.10 | USD 2.40 | USD 1.027 | 262,144 | not stated | Moonshot AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotmoonshotai/Kimi-K2.6Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.60 $2.80 $0.12” | USD 0.60 | USD 0.12 | USD 2.80 | USD 1.15 | 262,144 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra prioritymoonshotai/Kimi-K2.6Notes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $1.125 $5.25 $0.225” | USD 1.125 | USD 0.225 | USD 5.25 | USD 2.156 | 262,144 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (batch, flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Kimi K2.6 cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Chutes | USD 48.55 | USD 95.33 | USD 326.97 |
| CoreWeave Forge | USD 92.88 | USD 171.15 | USD 711.90 |
| SiliconFlow | USD 96.48 | USD 190.44 | USD 728.10 |
| DeepInfra | USD 98.10 | USD 189.30 | USD 747.00 |
| Parasail | USD 98.64 | USD 190.02 | USD 762.30 |
| Venice | USD 98.64 | USD 190.02 | USD 762.30 |
| Featherless | USD 98.32 | USD 196.49 | USD 757.62 |
| Novita AI | USD 98.64 | USD 196.92 | USD 766.80 |
| Moonshot AI (maker) | USD 114.84 | USD 231.12 | USD 861.30 |
| Baidu | USD 114.84 | USD 231.12 | USD 861.30 |
| Cloudflare Workers AI | USD 114.84 | USD 231.12 | USD 861.30 |
| DigitalOcean | USD 116.46 | USD 233.28 | USD 907.20 |
| Microsoft Azure | USD 126.32 | USD 254.23 | USD 947.43 |
For the support chatbot, the cheapest price (Chutes, USD 48.55 a month) saves USD 50.09 against the median (USD 98.64). For the coding agent the gap is USD 435.33 a month (57% lower).
Which Kimi K2.6 provider is cheapest for your traffic?
Chutes has the lowest input price (USD 0.39) and the lowest output price (USD 1.80), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Chutes | USD 0.7425 cheapest | USD 0.6109 cheapest | USD 0.5056 cheapest |
| CoreWeave Forge | USD 1.34 | USD 1.153 | USD 1.002 |
| SiliconFlow | USD 1.427 | USD 1.191 | USD 1.002 |
| DeepInfra | USD 1.438 | USD 1.212 | USD 1.032 |
| Parasail | USD 1.438 | USD 1.216 | USD 1.039 |
| Venice | USD 1.438 | USD 1.216 | USD 1.039 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 7 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 13 providers publish a cached-input price below the input price: Chutes (90% off), CoreWeave Forge (77% off), SiliconFlow (82% off), DeepInfra (80% off), Parasail (79% off) and 8 more.
Context windows differ: 262,144 tokens at Chutes, CoreWeave Forge, SiliconFlow and 5 more; 256,000 tokens at Venice. Parasail, Cloudflare Workers AI, DigitalOcean and Microsoft Azure do not state one. The cheapest row is not always the one that fits a long prompt.
What does Kimi K2.6 cost in other languages?
The same text needs a different number of tokens in each language. With the Kimi K3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Kimi K2.6:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.085 | Chutes |
| Arabic MSA | USD 0.187 | Chutes |
| Hindi | USD 0.221 | Chutes |
| Chinese | USD 0.213 | Chutes |
| Code | USD 0.101 | Chutes |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Published benchmark results
BroadNet did not run these benchmarks; results are as published by the Moonshot AI model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| GPQA-Diamond | 90.5 | not stated | Moonshot AI model card, checked 2026-11-16 |
| SWE-Bench Verified | 80.2 | not stated | Moonshot AI model card, checked 2026-11-16 |
| LiveCodeBench (v6) | 89.6 | not stated | Moonshot AI model card, checked 2026-11-16 |
| HLE-Full (w/ tools) | 54.0 | not stated | Moonshot AI model card, checked 2026-11-16 |
| GPQA Diamond | 0.908 | Setting as listed by Epoch (no suffix); Epoch run kimi-k2.6, mean score on a 0 to 1 scale | Epoch AI, checked 2026-11-16 |
Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).
Estimate your own bill
- LLM API cost calculator with Kimi K2.6 preloaded: your traffic and cache rate, against any of 428 models.
- Kimi token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Kimi K2.6 compare with other Moonshot AI models?
The Moonshot AI models whose cheapest standard price is closest to Kimi K2.6's (USD 0.7425 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Kimi K2.5 | USD 0.45 | USD 2.25 | 262,144 | 8 |
| Kimi K2 Thinking | USD 0.80 | USD 1.20 | 262,144 | 6 |
| Kimi K2 Instruct | USD 0.57 | USD 2.30 | 131,072 | 2 |
| Kimi K2 Instruct 0905 | USD 0.60 | USD 2.50 | 262,144 | 2 |
| Kimi K2.7 Code | USD 0.60 | USD 3 | 262,144 | 12 |
| Kimi K3 | USD 1.85 | USD 9.50 | 1,048,576 | 18 |
Priced closest from other makers: Qwen2.5 Coder 32B Instruct (Qwen, USD 0.745) · GLM 4.7 (Z.ai, USD 0.7375) · Mistral Large 3 (Mistral AI, USD 0.75).
Compare Kimi K2.6 with
- Kimi K3 vs Kimi K2.6: API price side by side
- GLM 5.3 vs Kimi K2.6: API price side by side
- Kimi K2.6 vs Kimi K2.5: API price side by side
- Kimi K2.7 Code vs Kimi K2.6: API price side by side
Also compared: vs Kimi K3 · vs GLM 5.3 · vs Kimi K2.5 · vs Kimi K2.7 Code.
Every Kimi K2.6 price comparison · All model-vs-model price comparisons
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Kimi K2.6 API cost per token?
From USD 0.39 per 1M input tokens (USD 0.00000039 per token) and USD 1.80 per 1M output tokens (USD 0.0000018 per token) at the lowest standard prices we found. The median of 13 standard prices is USD 0.80 input and USD 3.50 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Kimi K2.6?
Among the 13 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Chutes, ranked on a blend of 3 input tokens to 1 output token (USD 0.7425 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is Kimi K2.6 cheaper from a host than from Moonshot AI?
Yes. Chutes charges USD 0.39 input and USD 1.80 output per 1M tokens, 57% below Moonshot AI's own USD 0.95 / USD 4 on the 3:1 blend.
Does Kimi K2.6 have cached input pricing?
All 13 standard prices include one. The lowest is USD 0.039 per 1M at Chutes; the median is USD 0.16. Providers without one bill cached input at the input price. What cached input means.
What is the Kimi K2.6 context window?
Up to 262,144 tokens. 1 standard price comes with less, down to 256,000 tokens (Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Kimi K2.6?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 326.97 a month at Chutes, USD 762.30 at the median price and USD 947.43 at Microsoft Azure. Try your own numbers.
Is there a batch, flex or priority price for Kimi K2.6?
Yes: batch from Moonshot AI at USD 0.57 / USD 2.40; flex / spot from DeepInfra at USD 0.60 / USD 2.80; priority from DeepInfra at USD 1.125 / USD 5.25 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Kimi K2.6 free to use through an API?
No provider in our data lists a free price for Kimi K2.6 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Kimi K2.6 open source, with open weights, and what is its licence?
Moonshot AI publishes the weights on Hugging Face as moonshotai/Kimi-K2.6, in a public repository with no access gate. The licence, as the Moonshot AI model card states it: Modified MIT License. Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Moonshot AI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does Kimi K2.6 have?
Total parameters, as the Moonshot AI model card states them: 1T. Active parameters per token: 32B. (checked 2026-11-16; BroadNet did not verify these figures.)
Does Kimi K2.6 support tool calling?
Yes, according to the Moonshot AI model card: “K2.6 shares the same design of Interleaved Thinking and Multi-Step Tool Call as K2 Thinking.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.
How do I call Kimi K2.6 with the OpenAI SDK?
BroadNet does not serve Kimi K2.6. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model moonshotai/Kimi-K2.6). Each provider page quotes the provider's docs with a check date.
How does Kimi K2.6 score on benchmarks?
As published, the Moonshot AI model card reports 90.5 on GPQA-Diamond and 80.2 on SWE-Bench Verified; Epoch AI measured 0.908 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Microsoft Azure: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DigitalOcean: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Moonshot AI: own API pricing (checked 2026-11-14)
- Moonshot AI: own API pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Parasail: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)