Phi-4-mini vs Gemini 2.5 Flash-Lite vs Nova Lite
Gemini 2.5 Flash-Lite comes out ahead, 85 to 77 and 58 on our weighted score, though Nova Lite is 40% cheaper per token.
MicrosoftPhi-4-mini
58/100- ECI—
- Price$0.075 / $0.30
- Context128K
- Our pick
GoogleGemini 2.5 Flash-Lite
85/100- ECI133.9
- Price$0.10 / $0.40
- Context1.05M
AmazonNova Lite
77/100- ECI—
- Price$0.06 / $0.24
- Context300K
Gemini 2.5 Flash-Lite is our pick
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 85/100 against Nova Lite (77) and Phi-4-mini (58). It leads on inputs & features and context window. Nova Lite 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 priceNova LiteNova Lite $0.105 · Phi-4-mini $0.131 · Gemini 2.5 Flash-Lite $0.175 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Nova Lite 300,000 · Phi-4-mini 128,000 tokens
- Widest inputsGemini 2.5 Flash-LitePhi-4-mini: Text · Gemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video · Nova Lite: Text, Images, PDFs, Video
- Self-hostingPhi-4-miniPublishes downloadable weights
| Measure | Weight | Phi-4-mini | Gemini 2.5 Flash-Lite | Nova Lite |
|---|---|---|---|---|
| Price | 50% | 92 | 86 | 96 |
| Inputs & features | 30% | 25 | 100 | 70 |
| Context window | 20% | 24 | 61 | 39 |
| Overall | 100% | 58/100 | 85/100 | 77/100 |
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 | Phi-4-miniMicrosoft | Gemini 2.5 Flash-LiteGoogle | Nova LiteAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 133.9 | — |
| ECI rank | — | #118 of 148 | — |
| Price per million tokens | |||
| Input | $0.075 | $0.10 | $0.06 (best) |
| Output | $0.30 | $0.40 | $0.24 (best) |
| Cached input | — | $0.01 (best) | $0.015 |
| Blended (3:1) | $0.131 | $0.175 | $0.105 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Azure API | Official Google API | Official Amazon Bedrock API |
| Limits | |||
| Context window | 128,000 tokens | 1,048,576 tokens (best) | 300,000 tokens |
| Max output | 4,096 tokens | 65,536 tokens (best) | 10,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | Yes | No |
| Video | No | Yes | Yes |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | phi-4-mini | gemini-2.5-flash-lite | amazon.nova-lite-v1:0 |
| API providers | 1 | 20 (best) | 3 |
| Released | Dec 11, 2024 | Jun 17, 2025 | Dec 3, 2024 |
| Knowledge cutoff | Oct 2023 | Jan 2025 | Oct 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Phi-4-mini$1.35
- Gemini 2.5 Flash-Lite$1.80
- Nova Lite$1.08
Which should you choose?
Which is better: Phi-4-mini, Gemini 2.5 Flash-Lite or Nova Lite?
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 85/100 against Nova Lite (77) and Phi-4-mini (58). It leads on inputs & features and context window. Nova Lite 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, Phi-4-mini, Gemini 2.5 Flash-Lite or Nova Lite?
Nova Lite is cheaper at $0.06 input / $0.24 output per million tokens (official Amazon Bedrock API price). Phi-4-mini costs $0.075 input / $0.30 output per million tokens (official Azure API price); Gemini 2.5 Flash-Lite costs $0.10 input / $0.40 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.105 per million tokens for Nova Lite versus $0.131 for Phi-4-mini (1.2× as much) and $0.175 for Gemini 2.5 Flash-Lite (1.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Phi-4-mini has not been scored yet, Gemini 2.5 Flash-Lite has an ECI of 133.9 and Nova Lite has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Phi-4-mini, Gemini 2.5 Flash-Lite and Nova Lite 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 2.5 Flash-Lite has the largest context window at 1,048,576 tokens, against 300,000 for Nova Lite and 128,000 for Phi-4-mini. Maximum output per response: Phi-4-mini up to 4,096, Gemini 2.5 Flash-Lite up to 65,536, Nova Lite up to 10,000 tokens.
Which can read images, PDFs, audio or video?
Phi-4-mini accepts text; Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video; Nova Lite accepts text, images, PDFs and video. Gemini 2.5 Flash-Lite handles the widest range of inputs.
Are any of these open source?
Phi-4-mini publishes its weights and can be self-hosted; Gemini 2.5 Flash-Lite and Nova Lite is proprietary.
Which is newer?
Gemini 2.5 Flash-Lite is the newest, released Jun 17, 2025. Phi-4-mini came out Dec 11, 2024; Nova Lite came out Dec 3, 2024. Knowledge cutoff: Phi-4-mini Oct 2023, Gemini 2.5 Flash-Lite Jan 2025, Nova Lite Oct 2024.
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.
