Gemini 3.1 Flash Lite Preview vs Phi-4-mini vs MiniMax-M2 Her
Gemini 3.1 Flash Lite Preview comes out ahead, 73 to 58 and 45 on our weighted score, though Phi-4-mini is 4.3× cheaper per token.
- Our pick
GoogleGemini 3.1 Flash Lite Preview
73/100- ECI—
- Price$0.25 / $1.50
- Context1.05M
MicrosoftPhi-4-mini
58/100- ECI—
- Price$0.075 / $0.30
- Context128K
MiniMaxMiniMax-M2 Her
45/100- ECI—
- Price$0.30 / $1.20
- Context66K
Gemini 3.1 Flash Lite Preview is our pick
Gemini 3.1 Flash Lite Preview is the better all-round choice, scoring 73/100 against Phi-4-mini (58) and MiniMax-M2 Her (45). It leads on inputs & features and context window. Phi-4-mini wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest pricePhi-4-miniPhi-4-mini $0.131 · MiniMax-M2 Her $0.525 · Gemini 3.1 Flash Lite Preview $0.563 per 1M tokens (3:1 blend)
- Longest contextGemini 3.1 Flash Lite PreviewGemini 3.1 Flash Lite Preview 1,048,576 · Phi-4-mini 128,000 · MiniMax-M2 Her 65,536 tokens
- Widest inputsGemini 3.1 Flash Lite PreviewGemini 3.1 Flash Lite Preview: Text, Images, PDFs, Audio, Video · Phi-4-mini: Text · MiniMax-M2 Her: Text
- Self-hostingPhi-4-miniPublishes downloadable weights
| Measure | Weight | Gemini 3.1 Flash Lite Preview | Phi-4-mini | MiniMax-M2 Her |
|---|---|---|---|---|
| Price | 50% | 62 | 92 | 63 |
| Inputs & features | 30% | 100 | 25 | 35 |
| Context window | 20% | 61 | 24 | 12 |
| Overall | 100% | 73/100 | 58/100 | 45/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini 3.1 Flash Lite PreviewGoogle | Phi-4-miniMicrosoft | MiniMax-M2 HerMiniMax |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.25 | $0.075 (best) | $0.30 |
| Output | $1.50 | $0.30 (best) | $1.20 |
| Cached input | $0.025 | — | — |
| Blended (3:1) | $0.563 | $0.131 (best) | $0.525 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Google API | Official Azure API | Median of 4 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 128,000 tokens | 65,536 tokens |
| Max output | 65,536 tokens (best) | 4,096 tokens | 2,048 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yesminimal · low · medium · high | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | gemini-3.1-flash-lite-preview | phi-4-mini | — |
| API providers | 10 (best) | 1 | 4 |
| Released | Mar 3, 2026 | Dec 11, 2024 | Jan 23, 2026 |
| Knowledge cutoff | Jan 2025 | Oct 2023 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 3.1 Flash Lite Preview$5.50
- Phi-4-mini$1.35
- MiniMax-M2 Her$5.40
Which should you choose?
Which is better: Gemini 3.1 Flash Lite Preview, Phi-4-mini or MiniMax-M2 Her?
Gemini 3.1 Flash Lite Preview is the better all-round choice, scoring 73/100 against Phi-4-mini (58) and MiniMax-M2 Her (45). It leads on inputs & features and context window. Phi-4-mini wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemini 3.1 Flash Lite Preview, Phi-4-mini or MiniMax-M2 Her?
Phi-4-mini is cheaper at $0.075 input / $0.30 output per million tokens (official Azure API price). MiniMax-M2 Her costs $0.30 input / $1.20 output per million tokens (median across 4 API providers); Gemini 3.1 Flash Lite Preview costs $0.25 input / $1.50 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.131 per million tokens for Phi-4-mini versus $0.525 for MiniMax-M2 Her (4× as much) and $0.563 for Gemini 3.1 Flash Lite Preview (4.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini 3.1 Flash Lite Preview has not been scored yet, Phi-4-mini has not been scored yet and MiniMax-M2 Her has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 3.1 Flash Lite Preview, Phi-4-mini and MiniMax-M2 Her yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3.1 Flash Lite Preview has the largest context window at 1,048,576 tokens, against 128,000 for Phi-4-mini and 65,536 for MiniMax-M2 Her. Maximum output per response: Gemini 3.1 Flash Lite Preview up to 65,536, Phi-4-mini up to 4,096, MiniMax-M2 Her up to 2,048 tokens.
Which can read images, PDFs, audio or video?
Gemini 3.1 Flash Lite Preview accepts text, images, PDFs, audio and video; Phi-4-mini accepts text; MiniMax-M2 Her accepts text. Gemini 3.1 Flash Lite Preview handles the widest range of inputs.
Are any of these open source?
Phi-4-mini publishes its weights and can be self-hosted; Gemini 3.1 Flash Lite Preview and MiniMax-M2 Her is proprietary.
Which is newer?
Gemini 3.1 Flash Lite Preview is the newest, released Mar 3, 2026. MiniMax-M2 Her came out Jan 23, 2026; Phi-4-mini came out Dec 11, 2024. Knowledge cutoff: Gemini 3.1 Flash Lite Preview Jan 2025, Phi-4-mini Oct 2023.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
