BroadRouter

Kimi K3 vs Kimi K2.6 API pricing

Updated

Kimi K3: USD 1.85 input, USD 9.50 output per 1M tokens (Chutes). Kimi K2.6: USD 0.39 input, USD 1.80 output per 1M tokens (Chutes). At 3 input tokens per output token, Kimi K3 costs 5.1× as much as Kimi K2.6 (USD 3.763 vs USD 0.7425 per 1M).

Kimi K3 and Kimi K2.6 are releases in the same family. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-16), with no claim about quality, speed or accuracy.

How do Kimi K3 and Kimi K2.6 differ on price?

Kimi K3 and Kimi K2.6 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Kimi K3 and Kimi K2.6 API prices compared
PriceKimi K3Kimi K2.6
Model pageKimi K3
Moonshot AI · 23 providers
Kimi K2.6
Moonshot AI · 13 providers
Cheapest standard price, blended 3:1USD 3.763
USD 1.85 in / USD 9.50 out at Chutes
Chutes page checked 2026-11-15
USD 0.7425 lower
USD 0.39 in / USD 1.80 out at Chutes
Chutes page checked 2026-11-15
Cheapest inputUSD 1.85
Chutes source
USD 0.39 lower
Chutes source
Cheapest cached inputUSD 0.185
Chutes source
USD 0.039 lower
Chutes source
Cheapest outputUSD 9.50
Chutes source
USD 1.80 lower
Chutes source
Maker's own APIUSD 3 / USD 15
Moonshot AI source
USD 0.95 / USD 4
Moonshot AI source
Median standard priceUSD 3 / USD 15
input / output, 23 prices
USD 0.80 / USD 3.50
input / output, 13 prices
Context window1,048,576 tokens, largest stated; from 262,144 at some providers262,144 tokens, largest stated; from 256,000 at some providers
Providers with a standard price2313

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Kimi K3 and Kimi K2.6 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Kimi K3 and Kimi K2.6
WorkloadKimi K3Kimi K2.6Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 247.59
Chutes
USD 48.55
Chutes
USD 199.04
Kimi K2.6 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 466.62
Chutes
USD 95.33
Chutes
USD 371.29
Kimi K2.6 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 1,638
Chutes
USD 326.97
Chutes
USD 1,311
Kimi K2.6 lower

Kimi K2.6 is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 5.1× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

Kimi K2.6 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Kimi K3's, so the input:output ratio never changes the answer.

Price per 1M tokens of Kimi K3 and Kimi K2.6 at different input:output mixes
Input : output tokensKimi K3Kimi K2.6
1 : 3 (long answers)USD 7.588
Chutes
USD 1.448 lower
Chutes
1 : 1USD 5.675
Chutes
USD 1.095 lower
Chutes
3 : 1 (the site’s blend)USD 3.763
Chutes
USD 0.7425 lower
Chutes
10 : 1 (retrieval, long prompts)USD 2.545
Chutes
USD 0.5182 lower
Chutes
30 : 1 (agents, big contexts)USD 2.097
Chutes
USD 0.4355 lower
Chutes

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Kimi K3 and Kimi K2.6 cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Kimi K3 tokenizer for Kimi K3 (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, Kimi K3 and Kimi K2.6
ContentKimi K3Kimi K2.6
EnglishUSD 0.402
Chutes
USD 0.085 lower
Chutes
Arabic MSAUSD 0.887
Chutes
USD 0.187 lower
Chutes
Egyptian ArabicUSD 0.892
Chutes
USD 0.188 lower
Chutes
HindiUSD 1.05
Chutes
USD 0.221 lower
Chutes
ChineseUSD 1.01
Chutes
USD 0.213 lower
Chutes
SpanishUSD 0.542
Chutes
USD 0.114 lower
Chutes
CodeUSD 0.480
Chutes
USD 0.101 lower
Chutes

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

More comparisons: Kimi K3.1 Pro vs Kimi K3 · Claude Sonnet 5.5 vs Kimi K3 · Qwen3.8 Max vs Kimi K3 · GLM 5.3 vs Kimi K3 · DeepSeek V4 Pro vs Kimi K3 · Kimi K3 vs MiniMax M3 · GLM 5.3 vs Kimi K2.6 · Kimi K2.6 vs Kimi K2.5 · Kimi K2.7 Code vs Kimi K2.6 · every Kimi K3 comparison · every Kimi K2.6 comparison · all 662 price comparisons

Questions

Is Kimi K3 cheaper than Kimi K2.6?

No. On a blend of 3 input tokens to 1 output token, Kimi K2.6 costs USD 0.7425 per 1M tokens and Kimi K3 USD 3.763, at each model's cheapest standard price. For input alone, Kimi K2.6 is cheaper (USD 0.39 against USD 1.85 per 1M); for output alone, Kimi K2.6 is (USD 1.80 against USD 9.50). This compares price only, not quality.

What do Kimi K3 and Kimi K2.6 cost per 1M tokens?

Kimi K3: from USD 1.85 input and USD 9.50 output at Chutes; Moonshot AI's own API charges USD 3 / USD 15; median of 23 standard prices USD 3 / USD 15. Kimi K2.6: from USD 0.39 input and USD 1.80 output at Chutes; Moonshot AI's own API charges USD 0.95 / USD 4; median of 13 standard prices USD 0.80 / USD 3.50. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Kimi K3 and Kimi K2.6?

10 providers have a standard price for both: Chutes (USD 3.763 and USD 0.7425 at 3:1), Featherless (USD 4 and USD 1.45 at 3:1), SiliconFlow (USD 5.40 and USD 1.427 at 3:1), DeepInfra (USD 5.70 and USD 1.438 at 3:1), Parasail (USD 6 and USD 1.438 at 3:1), Novita AI (USD 6 and USD 1.45 at 3:1), DigitalOcean (USD 6 and USD 1.712 at 3:1), Moonshot AI (USD 6 and USD 1.712 at 3:1), Microsoft Azure (USD 6 and USD 1.884 at 3:1), Venice (USD 7.50 and USD 1.438 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 3.763 and USD 0.7425.

Which is cheaper for a coding agent or a chatbot, Kimi K3 or Kimi K2.6?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,638 a month on Kimi K3 (Chutes) against USD 326.97 on Kimi K2.6 (Chutes), a difference of USD 1,311. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 247.59 a month on Kimi K3 (Chutes) against USD 48.55 on Kimi K2.6 (Chutes), a difference of USD 199.04. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Kimi K3 and Kimi K2.6 change?

Kimi K2.6 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Kimi K3's, so the input:output ratio never changes the answer.

Do Kimi K3 and Kimi K2.6 have cached input pricing?

Kimi K3 from USD 0.185 per 1M cached input tokens (Chutes; 22 of 23 standard prices list a discount). Kimi K2.6 from USD 0.039 per 1M cached input tokens (Chutes; 13 of 13 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Kimi K3 or Kimi K2.6?

Kimi K3: up to 1,048,576 tokens, against 262,144 for Kimi K2.6, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity