GPT-4.1 nano vs MiniMax-M3 vs Gemma 3 27B IT
MiniMax-M3 comes out ahead, 70 to 64 and 60 on our weighted score, though Gemma 3 27B IT is 3.5× cheaper per token.
Price in rating: Included · Exclude price
OpenAI
GPT-4.1 nano
64/100- ECI126.8
- Price$0.10 / $0.40
- Context1.05M
- Our pick
MiniMax
MiniMax-M3
70/100- ECI147.9
- Price$0.30 / $1.20
- Context1.05M
Google
Gemma 3 27B IT
60/100- ECI127.5
- Price$0.10 / $0.299
- Context131K
MiniMax-M3 is our pick
MiniMax-M3 is the better all-round choice, scoring 70/100 against GPT-4.1 nano (64) and Gemma 3 27B IT (60). It leads on capability and inputs & features. Gemma 3 27B IT wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityMiniMax-M3Capabilities Index (ECI): MiniMax-M3 147.9 · Gemma 3 27B IT 127.5 · GPT-4.1 nano 126.8
- Lowest priceGemma 3 27B ITGemma 3 27B IT $0.15 · GPT-4.1 nano $0.175 · MiniMax-M3 $0.525 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M3 and GPT-4.1 nanoMiniMax-M3 1,048,576 · GPT-4.1 nano 1,047,576 · Gemma 3 27B IT 131,072 tokens
- Widest inputsMiniMax-M3GPT-4.1 nano: Text, Images · MiniMax-M3: Text, Images, Video · Gemma 3 27B IT: Text, Images
- Self-hostingMiniMax-M3 and Gemma 3 27B ITPublishes downloadable weights
| Measure | Weight | GPT-4.1 nano | MiniMax-M3 | Gemma 3 27B IT |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 55 | 75 | 56 |
| Price | 25% | 82 | 60 | 85 |
| Inputs & features | 15% | 60 | 70 | 50 |
| Context window | 10% | 65 | 65 | 32 |
| Overall | 100% | 64/100 | 70/100 | 60/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 126.8 | 147.9 (best) | 127.5 |
| ECI rank | #142 of 158 | #77 of 158 (best) | #141 of 158 |
| GPQA DiamondGraduate-level science questions | 48.9% | 90.9% (best) | 47.7% |
| OTIS Mock AIME 2024–2025Competition mathematics | 28.9% | 71.1% (best) | 22.5% |
| SimpleQA VerifiedShort factual questions | 6.0% | — | — |
| Price per million tokens | |||
| Input | $0.10 (best) | $0.30 | $0.10 (best) |
| Output | $0.40 | $1.20 | $0.299 (best) |
| Cached input | $0.025 (best) | $0.06 | — |
| Blended (3:1) | $0.175 | $0.525 | $0.15 (best) |
| Long-context rate | Same rate | Over 512K: $0.60 / $2.40 | Same rate |
| Price source | Official OpenAI API | Official MiniMax (minimax.io) API | Median of 17 providers |
| Limits | |||
| Context window | 1,047,576 tokens | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | 32,768 tokens | 512,000 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gpt-4.1-nano | MiniMax-M3 | — |
| API providers | 22 | 52 (best) | 18 |
| Released | Apr 14, 2025 | Jun 1, 2026 | Mar 12, 2025 |
| Knowledge cutoff | Apr 2024 | — | Aug 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
GPT-4.1 nano$1.80
MiniMax-M3$5.40
Gemma 3 27B IT$1.60
Which should you choose?
Which is better: GPT-4.1 nano, MiniMax-M3 or Gemma 3 27B IT?
MiniMax-M3 is the better all-round choice, scoring 70/100 against GPT-4.1 nano (64) and Gemma 3 27B IT (60). It leads on capability and inputs & features. Gemma 3 27B IT wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-4.1 nano, MiniMax-M3 or Gemma 3 27B IT?
Gemma 3 27B IT is cheaper at $0.10 input / $0.299 output per million tokens (median across 17 API providers). GPT-4.1 nano costs $0.10 input / $0.40 output per million tokens (official OpenAI API price); MiniMax-M3 costs $0.30 input / $1.20 output per million tokens (official MiniMax (minimax.io) API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Gemma 3 27B IT versus $0.175 for GPT-4.1 nano (1.2× as much) and $0.525 for MiniMax-M3 (3.5× as much).
Which scores higher on benchmarks?
MiniMax-M3 scores higher on the Capabilities Index (ECI): MiniMax-M3 147.9 (#77 of 158), Gemma 3 27B IT 127.5 (#141 of 158) and GPT-4.1 nano 126.8 (#142 of 158). Their confidence ranges do not overlap (145.8–150.0 vs 124.4–130.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — MiniMax-M3 90.9%, GPT-4.1 nano 48.9%, Gemma 3 27B IT 47.7%; OTIS Mock AIME 2024–2025 — MiniMax-M3 71.1%, GPT-4.1 nano 28.9%, Gemma 3 27B IT 22.5%.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-4.1 nano, MiniMax-M3 and Gemma 3 27B IT yet, so there is no like-for-like coding score. On overall capability, MiniMax-M3 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
MiniMax-M3 and GPT-4.1 nano have the largest context windows (1,048,576 and 1,047,576 tokens), against 131,072 for Gemma 3 27B IT. Maximum output per response: GPT-4.1 nano up to 32,768, MiniMax-M3 up to 512,000, Gemma 3 27B IT up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GPT-4.1 nano accepts text and images; MiniMax-M3 accepts text, images and video; Gemma 3 27B IT accepts text and images. MiniMax-M3 handles the widest range of inputs.
Are any of these open source?
MiniMax-M3 and Gemma 3 27B IT publishes its weights and can be self-hosted; GPT-4.1 nano is proprietary.
Which is newer?
MiniMax-M3 is the newest, released Jun 1, 2026. GPT-4.1 nano came out Apr 14, 2025; Gemma 3 27B IT came out Mar 12, 2025. Knowledge cutoff: GPT-4.1 nano Apr 2024, Gemma 3 27B IT Aug 2024.
How do you decide the winner?
This rating uses 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 Nov 18, 2026.