Kimi K2.7 Code vs Kimi K2.6 API pricing
Updated
Kimi K2.7 Code: USD 0.60 input, USD 3 output per 1M tokens (CoreWeave Forge). Kimi K2.6: USD 0.39 input, USD 1.80 output per 1M tokens (Chutes). At 3 input tokens per output token, Kimi K2.7 Code costs 62% more than Kimi K2.6 (USD 1.20 vs USD 0.7425 per 1M).
How do Kimi K2.7 Code and Kimi K2.6 differ on price?
- Cheapest input price: Kimi K2.6 USD 0.39 against USD 0.60 per 1M tokens, so Kimi K2.7 Code costs 1.54× as much (54% more).
- Cheapest output price: Kimi K2.6 USD 1.80 against USD 3 per 1M tokens, so Kimi K2.7 Code costs 1.67× as much (67% more).
- Among the 198 indexed models, Kimi K2.7 Code ranks 135th cheapest and Kimi K2.6 114th on the 3:1 blend.
- No input:output mix changes the answer: Kimi K2.6 is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Kimi K2.7 Code at 11 standard prices of 12, from USD 0.12 (CoreWeave Forge, 80% below that provider's input price); Kimi K2.6 at 13 standard prices of 13, from USD 0.039 (Chutes, 90% below that provider's input price).
- Both state a context window of up to 262,144 tokens.
- Kimi K2.6 has 13 providers with a standard price, 1 more than Kimi K2.7 Code; 10 providers sell both (Chutes, CoreWeave Forge, Parasail, Venice and 6 more).
- On one account, Chutes charges USD 1.499 for Kimi K2.7 Code (1.25× its cheapest price) and USD 0.7425 for Kimi K2.6 (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Kimi K2.6: its dearest standard price is 2.5× its cheapest, against 1.43× for Kimi K2.7 Code.
- Moonshot AI's own API charges USD 1.712 for Kimi K2.7 Code at 3:1, 43% above the cheapest provider (CoreWeave Forge).
- Moonshot AI's own API charges USD 1.712 for Kimi K2.6 at 3:1, 131% above the cheapest provider (Chutes).
- Kimi K2.7 Code has a batch price at 1 provider, from USD 1.027 at 3:1 (Moonshot AI); Kimi K2.6 has a batch price at 1 provider, from USD 1.027 at 3:1 (Moonshot AI).
- For the one-developer coding agent preset, the gap is USD 3,464 a year in Kimi K2.6's favour (Kimi K2.7 Code USD 615.60 a month, Kimi K2.6 USD 326.97).
- Per character of input, Kimi K2.7 Code costs 1.54× as much as Kimi K2.6 in every measured language, because both use the Kimi K3 tokenizer.
Kimi K2.7 Code 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.
| Price | Kimi K2.7 Code | Kimi K2.6 |
|---|---|---|
| Model page | Kimi K2.7 Code Moonshot AI · 12 providers | Kimi K2.6 Moonshot AI · 13 providers |
| Cheapest standard price, blended 3:1 | USD 1.20 USD 0.60 in / USD 3 out at CoreWeave Forge CoreWeave Forge 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 input | USD 0.60 CoreWeave Forge source | USD 0.39 lower Chutes source |
| Cheapest cached input | USD 0.12 CoreWeave Forge source | USD 0.039 lower Chutes source |
| Cheapest output | USD 3 CoreWeave Forge source | USD 1.80 lower Chutes source |
| Maker's own API | USD 0.95 / USD 4 Moonshot AI source | USD 0.95 / USD 4 Moonshot AI source |
| Median standard price | USD 0.90458 / USD 3.90 input / output, 12 prices | USD 0.80 / USD 3.50 input / output, 13 prices |
| Context window | 262,144 tokens, largest stated; from 256,000 at some providers | 262,144 tokens, largest stated; from 256,000 at some providers |
| Providers with a standard price | 12 | 13 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Kimi K2.7 Code 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).
| Workload | Kimi K2.7 Code | Kimi K2.6 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 82.08 CoreWeave Forge | USD 48.55 Chutes | USD 33.53 Kimi K2.6 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 154.44 CoreWeave Forge | USD 95.33 Chutes | USD 59.11 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 615.60 CoreWeave Forge | USD 326.97 Chutes | USD 288.63 Kimi K2.6 lower |
Kimi K2.6 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 88% more than 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 K2.7 Code's, so the input:output ratio never changes the answer.
| Input : output tokens | Kimi K2.7 Code | Kimi K2.6 |
|---|---|---|
| 1 : 3 (long answers) | USD 2.40 CoreWeave Forge | USD 1.448 lower Chutes |
| 1 : 1 | USD 1.80 CoreWeave Forge | USD 1.095 lower Chutes |
| 3 : 1 (the site’s blend) | USD 1.20 CoreWeave Forge | USD 0.7425 lower Chutes |
| 10 : 1 (retrieval, long prompts) | USD 0.8182 CoreWeave Forge | USD 0.5182 lower Chutes |
| 30 : 1 (agents, big contexts) | USD 0.6774 CoreWeave Forge | 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 K2.7 Code 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 K2.7 Code (the same one for both, so the gap equals the price gap):
| Content | Kimi K2.7 Code | Kimi K2.6 |
|---|---|---|
| English | USD 0.130 CoreWeave Forge | USD 0.085 lower Chutes |
| Arabic MSA | USD 0.288 CoreWeave Forge | USD 0.187 lower Chutes |
| Egyptian Arabic | USD 0.289 CoreWeave Forge | USD 0.188 lower Chutes |
| Hindi | USD 0.341 CoreWeave Forge | USD 0.221 lower Chutes |
| Chinese | USD 0.327 CoreWeave Forge | USD 0.213 lower Chutes |
| Spanish | USD 0.176 CoreWeave Forge | USD 0.114 lower Chutes |
| Code | USD 0.156 CoreWeave Forge | 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.
Published results on the same benchmark
BroadNet did not run these benchmarks. BroadRouter is BroadNet's site. Each row pairs results from one source with the same setting for both models, as published; results from different sources or settings are never put side by side. One benchmark says little about your own workload.
| Benchmark | Kimi K2.7 Code | Kimi K2.6 | Source and setting |
|---|---|---|---|
| GPQA Diamond | 0.879 | 0.908 | Epoch AI, checked 2026-11-16 Setting as listed by Epoch (no suffix), mean score on a 0 to 1 scale |
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).
All published results for each model, with every setting: Kimi K2.7 Code · Kimi K2.6.
Check it on your own traffic
- Kimi K2.7 Code API pricing: all 12 providers and other tiers.
- Kimi K2.6 API pricing: all 13 providers and other tiers.
- Cost calculator with Kimi K2.7 Code and Kimi K2.6 preloaded
- Kimi token counter
- Prompt caching calculator
More comparisons: GLM 5.3 vs Kimi K2.7 Code · Kimi K3 vs Kimi K2.6 · GLM 5.3 vs Kimi K2.6 · Kimi K2.6 vs Kimi K2.5 · every Kimi K2.7 Code comparison · every Kimi K2.6 comparison · all 651 price comparisons
Questions
Is Kimi K2.7 Code 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 K2.7 Code USD 1.20, at each model's cheapest standard price. For input alone, Kimi K2.6 is cheaper (USD 0.39 against USD 0.60 per 1M); for output alone, Kimi K2.6 is (USD 1.80 against USD 3). This compares price only, not quality.
What do Kimi K2.7 Code and Kimi K2.6 cost per 1M tokens?
Kimi K2.7 Code: from USD 0.60 input and USD 3 output at CoreWeave Forge; Moonshot AI's own API charges USD 0.95 / USD 4; median of 12 standard prices USD 0.90458 / USD 3.90. 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 K2.7 Code and Kimi K2.6?
10 providers have a standard price for both: Chutes (USD 1.499 and USD 0.7425 at 3:1), CoreWeave Forge (USD 1.20 and USD 1.34 at 3:1), Parasail (USD 1.438 and USD 1.438 at 3:1), Venice (USD 1.438 and USD 1.438 at 3:1), Featherless (USD 1.45 and USD 1.45 at 3:1), SiliconFlow (USD 1.594 and USD 1.427 at 3:1), Novita AI (USD 1.712 and USD 1.45 at 3:1), Cloudflare Workers AI (USD 1.712 and USD 1.712 at 3:1), Moonshot AI (USD 1.712 and USD 1.712 at 3:1), Microsoft Azure (USD 1.712 and USD 1.884 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 1.20 and USD 0.7425.
Which is cheaper for a coding agent or a chatbot, Kimi K2.7 Code 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 615.60 a month on Kimi K2.7 Code (CoreWeave Forge) against USD 326.97 on Kimi K2.6 (Chutes), a difference of USD 288.63. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 82.08 a month on Kimi K2.7 Code (CoreWeave Forge) against USD 48.55 on Kimi K2.6 (Chutes), a difference of USD 33.53. 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 K2.7 Code 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 K2.7 Code's, so the input:output ratio never changes the answer.
Do Kimi K2.7 Code and Kimi K2.6 have cached input pricing?
Kimi K2.7 Code from USD 0.12 per 1M cached input tokens (CoreWeave Forge; 11 of 12 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 K2.7 Code or Kimi K2.6?
Both go up to 262,144 tokens on the providers that state it.
Which scores higher on GPQA Diamond, Kimi K2.7 Code or Kimi K2.6?
Per Epoch AI (checked 2026-11-16), Kimi K2.7 Code scores 0.879 and Kimi K2.6 scores 0.908 on GPQA Diamond (Setting as listed by Epoch (no suffix), mean score on a 0 to 1 scale). BroadNet did not run these benchmarks, and one benchmark says little about your own workload. Every result both models share, with sources.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- CoreWeave Forge: pricing (checked 2026-11-15)
- Moonshot AI: own API pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Parasail: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)
- SiliconFlow: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Microsoft Azure: pricing (checked 2026-11-14)
- Microsoft Azure: pricing (checked 2026-11-14)
- Moonshot AI: own API pricing (checked 2026-11-14)
- Epoch AI benchmark data, CC BY 4.0 (checked 2026-11-16)