Gemma 4 31B vs Kimi K2.7 Code
At a Glance
| Compare | Gemma 4 31BGoogle DeepMind | 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 | $0.090Openrouter ↗ · Sep 22, 2026 | $0.68Deepinfra ↗ · Sep 22, 2026 |
| Output priceFrom · USD / 1M tokens | $0.34Openrouter ↗ · Sep 22, 2026 | $3.21Openrouter ↗ · Sep 22, 2026 |
| Context windowMaximum documented tokens | 262K | 262K |
| Model facts checked | Sep 3, 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 | Gemma 4 31B | Kimi K2.7 Code |
|---|---|---|
| Developer | Google DeepMind | Moonshot AI |
| Family | Gemma 4 | Kimi K2 7 |
| Model | Gemma 4 31B | Kimi K2.7 Code |
| Version | Gemma 4 31B | Kimi K2.7 Code |
| Lifecycle | active | active |
| Released | 2026-03-11 | 2026-06-11 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text, Image, Video |
| Output modalities | Text | Text |
| Context window | 262K | 262K |
| Total parameters | 31B | 1T |
| Active parameters | Unknown | 32B |
| License | apache-2.0 | modified-mit |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Cerebras (Standard), Deepinfra (Standard), Google Gemini (Standard), Openrouter (Standard), Together Ai (Standard) | Deepinfra (Standard), Fireworks Ai (Standard), Openrouter (Standard), Together Ai (Standard) |
| Capabilities | chat, generation, reasoning, structured_outputs, tools | agents, chat, coding, reasoning, tools, vision |
Gemma 4 31B Capabilities
Kimi K2.7 Code Capabilities
Primary Evidence
Sources and Freshness
Questions
Gemma 4 31B vs Kimi K2.7 Code FAQs
Is Gemma 4 31B or Kimi K2.7 Code better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Gemma 4 31B and Kimi K2.7 Code, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Gemma 4 31B or Kimi K2.7 Code?+
Gemma 4 31B is $0.090 and Kimi K2.7 Code is $0.68 per million tokens, so Gemma 4 31B is cheaper on this metric. Gemma 4 31B is $0.34 and Kimi K2.7 Code is $3.21 per million tokens, so Gemma 4 31B is cheaper on this metric.
Which has a larger context window, Gemma 4 31B or Kimi K2.7 Code?+
Neither model has a larger sourced context window in this comparison. Gemma 4 31B is 262K and Kimi K2.7 Code is 262K.
Which performs better in benchmarks, Gemma 4 31B 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 Gemma 4 31B or Kimi K2.7 Code be self-hosted?+
Both models have the same recorded self-hosting status: supported. Gemma 4 31B is open weight; Kimi K2.7 Code is open weight.
Can Gemma 4 31B and Kimi K2.7 Code understand images?+
Gemma 4 31B is 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, Gemma 4 31B or Kimi K2.7 Code?+
Neither has a larger sourced maximum output. Gemma 4 31B is — and Kimi K2.7 Code is —.
Do Gemma 4 31B and Kimi K2.7 Code support reasoning and tool use?+
Gemma 4 31B: reasoning, tool calling, and image input. Kimi K2.7 Code: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, Gemma 4 31B or Kimi K2.7 Code?+
Gemma 4 31B has 5 sourced provider routes; Kimi K2.7 Code has 4, so Gemma 4 31B has broader tracked availability.
Which offers better value, Gemma 4 31B 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.