MiniMax M2.7 vs Gemma 4 31B
At a Glance
| Compare |  MiniMax M2.7MiniMax |  Gemma 4 31BGoogle DeepMind |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.25Deepinfra ↗ · Sep 3, 2026 | $0.090Openrouter ↗ · Sep 23, 2026 |
| Output priceFrom · USD / 1M tokens | $1.00Deepinfra ↗ · Sep 3, 2026 | $0.34Openrouter ↗ · Sep 23, 2026 |
| Context windowMaximum documented tokens | 205K | 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
| Benchmark | MiniMax-M2.7 | Gemma 4 31B |
|---|---|---|
| LMArena Text Arenatext-2026-09-13-d25aabda0010 · arena_rating · leader | 1,404.6197% of row best · rating · minimax-m2.7; 95% CI [1401.03588542, 1408.19095698]; votes 69169; rank 138 | 1,441.68100% of row best · rating · gemma-4-31b; 95% CI [1434.13929794, 1449.22204224]; votes 5894; rank 64 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark winsNo overall winner | 1 benchmark winNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | MiniMax-M2.7 | Gemma 4 31B |
|---|---|---|
| Developer | MiniMax | Google DeepMind |
| Family | Minimax M2 7 | Gemma 4 |
| Model | MiniMax-M2.7 | Gemma 4 31B |
| Version | MiniMax-M2.7 | Gemma 4 31B |
| Lifecycle | active | active |
| Released | 2026-03-18 | 2026-03-11 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
| Context window | 205K | 262K |
| Total parameters | 228.7B | 31B |
| Active parameters | Unknown | Unknown |
| License | other | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Fireworks Ai (Standard), Hugging Face (Standard), Openrouter (Standard), Together Ai (Standard) | Cerebras (Standard), Deepinfra (Standard), Google Gemini (Standard), Openrouter (Standard), Together Ai (Standard) |
| Capabilities | chat, generation, tools | chat, generation, reasoning, structured_outputs, tools |
MiniMax M2.7 Capabilities
Gemma 4 31B Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
MiniMax-M2.7MiniMax | vs |  GPT-6 AstraOpenAI | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs | Claude Fable 5.1Anthropic | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs | Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs |  DeepSeek-V4.1-FlashDeepSeek | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs | Grok 4.6xAI | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs |  Qwen3.8-MaxQwen | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs |  Kimi-K3Moonshot AI | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs | MiniMax-M3MiniMax | family variantstext |
MiniMax-M2.7MiniMax | vs |  GLM-5.3Z.ai | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs |  Hy4 previewTencent | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs | Seed 2.1 ProByteDance Seed | cross-developer peerstext |
MiniMax-M2.7MiniMax | vs |  Mistral Large 3Mistral AI | cross-developer peerstext |
Primary Evidence
Sources and Freshness
Questions
MiniMax M2.7 vs Gemma 4 31B FAQs
Is MiniMax M2.7 or Gemma 4 31B better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both MiniMax M2.7 and Gemma 4 31B, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, MiniMax M2.7 or Gemma 4 31B?+
MiniMax M2.7 is $0.25 and Gemma 4 31B is $0.090 per million tokens, so Gemma 4 31B is cheaper on this metric. MiniMax M2.7 is $1.00 and Gemma 4 31B is $0.34 per million tokens, so Gemma 4 31B is cheaper on this metric.
Which has a larger context window, MiniMax M2.7 or Gemma 4 31B?+
Gemma 4 31B has the larger sourced context window. MiniMax M2.7 supports 205K and Gemma 4 31B supports 262K.
Which performs better in benchmarks, MiniMax M2.7 or Gemma 4 31B?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can MiniMax M2.7 or Gemma 4 31B be self-hosted?+
Both models have the same recorded self-hosting status: supported. MiniMax M2.7 is open weight; Gemma 4 31B is open weight.
Can MiniMax M2.7 and Gemma 4 31B understand images?+
MiniMax M2.7 is not documented with image input; Gemma 4 31B is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, MiniMax M2.7 or Gemma 4 31B?+
Neither has a larger sourced maximum output. MiniMax M2.7 is — and Gemma 4 31B is —.
Do MiniMax M2.7 and Gemma 4 31B support reasoning and tool use?+
MiniMax M2.7: tool calling. Gemma 4 31B: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, MiniMax M2.7 or Gemma 4 31B?+
MiniMax M2.7 has 5 sourced provider routes; Gemma 4 31B has 5, a tie.
Which offers better value, MiniMax M2.7 or Gemma 4 31B?+
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.