DeepSeek V4 Pro Base vs Kimi K2.7 Code
At a Glance
| Compare | DeepSeek V4 Pro BaseDeepSeek | Kimi K2.7 CodeMoonshot AI |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| CostLower is better · Published-token output estimate | UnrankedNot in the 44-model eligible cohort | #9 of 44$0.042 per LiveBench case |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | Not reported | $0.68Deepinfra ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | Not reported | $3.21Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 1,049K | 262K |
| Model facts checked | Aug 28, 2026View model evidence → | Sep 3, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | DeepSeek-V4-Pro-Base | Kimi K2.7 Code |
|---|---|---|
| Developer | DeepSeek | Moonshot AI |
| Family | Deepseek V4 Pro Base | Kimi K2 7 |
| Model | DeepSeek-V4-Pro-Base | Kimi K2.7 Code |
| Version | DeepSeek-V4-Pro-Base | Kimi K2.7 Code |
| Lifecycle | active | active |
| Released | 2026-04-24 | 2026-06-11 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image, Video |
| Output modalities | Text | Text |
| Context window | 1,049K | 262K |
| Total parameters | 1.6T | 1T |
| Active parameters | Unknown | 32B |
| License | Unknown | modified-mit |
| Open weights | Yes | Yes |
| API available | Unknown | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Unknown | Deepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard) |
| Capabilities | generation | agents, chat, coding, reasoning, tools, vision |
DeepSeek V4 Pro Base Capabilities
Kimi K2.7 Code Capabilities
Primary Evidence
Sources and Freshness
Questions
DeepSeek V4 Pro Base vs Kimi K2.7 Code FAQs
Is DeepSeek V4 Pro Base or Kimi K2.7 Code better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both DeepSeek V4 Pro Base and Kimi K2.7 Code, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
Only Kimi K2.7 Code has a directly sourced input price: $0.68 per million tokens. Only Kimi K2.7 Code has a directly sourced output price: $3.21 per million tokens.
Which has a larger context window, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
DeepSeek V4 Pro Base has the larger sourced context window. DeepSeek V4 Pro Base supports 1,049K and Kimi K2.7 Code supports 262K.
Which performs better in benchmarks, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can DeepSeek V4 Pro Base or Kimi K2.7 Code be self-hosted?+
Both models have the same recorded self-hosting status: supported. DeepSeek V4 Pro Base is open weight; Kimi K2.7 Code is open weight.
Can DeepSeek V4 Pro Base and Kimi K2.7 Code understand images?+
DeepSeek V4 Pro Base is not documented with image input; Kimi K2.7 Code is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
Neither has a larger sourced maximum output. DeepSeek V4 Pro Base is — and Kimi K2.7 Code is —.
Do DeepSeek V4 Pro Base and Kimi K2.7 Code support reasoning and tool use?+
DeepSeek V4 Pro Base: none of these features are definitively sourced. Kimi K2.7 Code: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
DeepSeek V4 Pro Base has 0 sourced provider routes; Kimi K2.7 Code has 4, so Kimi K2.7 Code has broader tracked availability.
Which offers better value, DeepSeek V4 Pro Base or Kimi K2.7 Code?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.