GPT-4.1 mini vs GPT-5.4 nano vs Mistral Medium 3
GPT-5.4 nano comes out ahead, 68 to 60 and 53 on our weighted score, and it is the cheaper option too.
OpenAIGPT-4.1 mini
60/100- ECI135.0
- Price$0.40 / $1.60
- Context1.05M
- Our pickOpenAI
GPT-5.4 nano
68/100- ECI145.8
- Price$0.20 / $1.25
- Context400K
Mistral AIMistral Medium 3
53/100- ECI134.1
- Price$0.40 / $2.00
- Context131K
GPT-5.4 nano is our pick
GPT-5.4 nano is the better all-round choice, scoring 68/100 against GPT-4.1 mini (60) and Mistral Medium 3 (53). It leads on capability and price. GPT-4.1 mini wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.4 nanoCapabilities Index (ECI): GPT-5.4 nano 145.8 · GPT-4.1 mini 135.0 · Mistral Medium 3 134.1
- Lowest priceGPT-5.4 nanoGPT-5.4 nano $0.463 · GPT-4.1 mini $0.70 · Mistral Medium 3 $0.80 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · GPT-5.4 nano 400,000 · Mistral Medium 3 131,072 tokens
- Widest inputsGPT-4.1 miniGPT-4.1 mini: Text, Images, PDFs · GPT-5.4 nano: Text, Images · Mistral Medium 3: Text, Images
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-4.1 mini | GPT-5.4 nano | Mistral Medium 3 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 59 | 73 | 58 |
| Price | 25% | 57 | 66 | 54 |
| Inputs & features | 15% | 70 | 70 | 50 |
| Context window | 10% | 61 | 44 | 24 |
| Overall | 100% | 60/100 | 68/100 | 53/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-4.1 miniOpenAI | GPT-5.4 nanoOpenAI | Mistral Medium 3Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 135.0 | 145.8 (best) | 134.1 |
| ECI rank | #115 of 148 | #75 of 148 (best) | #117 of 148 |
| GPQA DiamondGraduate-level science questions | 65.9% | 78.5% (best) | 59.5% |
| FrontierMath Tiers 1–3Research-level mathematics | 6.7% | 44.9% (best) | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 44.7% | 87.8% (best) | 32.2% |
| SimpleQA VerifiedShort factual questions | 12.7% (best) | 11.7% | — |
| Price per million tokens | |||
| Input | $0.40 | $0.20 (best) | $0.40 |
| Output | $1.60 | $1.25 (best) | $2.00 |
| Cached input | $0.10 | $0.02 (best) | — |
| Blended (3:1) | $0.70 | $0.463 (best) | $0.80 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official OpenAI API | Official Mistral API |
| Limits | |||
| Context window | 1,047,576 tokens (best) | 400,000 tokens | 131,072 tokens |
| Max output | 32,768 tokens | 128,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yeslow · medium · high · xhigh | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-4.1-mini | gpt-5.4-nano | mistral-medium-2505 |
| API providers | 24 | 26 (best) | 5 |
| Released | Apr 14, 2025 | Mar 17, 2026 | May 7, 2025 |
| Knowledge cutoff | Apr 2024 | Aug 31, 2025 | May 2025 |
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 mini$7.20
- GPT-5.4 nano$4.50
- Mistral Medium 3$8.00
Which should you choose?
Which is better: GPT-4.1 mini, GPT-5.4 nano or Mistral Medium 3?
GPT-5.4 nano is the better all-round choice, scoring 68/100 against GPT-4.1 mini (60) and Mistral Medium 3 (53). It leads on capability and price. GPT-4.1 mini wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-4.1 mini, GPT-5.4 nano or Mistral Medium 3?
GPT-5.4 nano is cheaper at $0.20 input / $1.25 output per million tokens (official OpenAI API price). GPT-4.1 mini costs $0.40 input / $1.60 output per million tokens (official OpenAI API price); Mistral Medium 3 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.463 per million tokens for GPT-5.4 nano versus $0.70 for GPT-4.1 mini (1.5× as much) and $0.80 for Mistral Medium 3 (1.7× as much).
Which scores higher on benchmarks?
GPT-5.4 nano scores higher on the Capabilities Index (ECI): GPT-5.4 nano 145.8 (#75 of 148), GPT-4.1 mini 135.0 (#115 of 148) and Mistral Medium 3 134.1 (#117 of 148). Their confidence ranges do not overlap (143.2–147.7 vs 131.2–136.6), so the gap is a real one. On individual benchmarks: GPQA Diamond — GPT-5.4 nano 78.5%, GPT-4.1 mini 65.9%, Mistral Medium 3 59.5%; OTIS Mock AIME 2024–2025 — GPT-5.4 nano 87.8%, GPT-4.1 mini 44.7%, Mistral Medium 3 32.2%.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-4.1 mini, GPT-5.4 nano and Mistral Medium 3 yet, so there is no like-for-like coding score. On overall capability, GPT-5.4 nano 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?
GPT-4.1 mini has the largest context window at 1,047,576 tokens, against 400,000 for GPT-5.4 nano and 131,072 for Mistral Medium 3. Maximum output per response: GPT-4.1 mini up to 32,768, GPT-5.4 nano up to 128,000, Mistral Medium 3 up to 131,072 tokens.
Which can read images, PDFs, audio or video?
GPT-4.1 mini accepts text, images and PDFs; GPT-5.4 nano accepts text and images; Mistral Medium 3 accepts text and images. GPT-4.1 mini handles the widest range of inputs.
Are any of these open source?
No. GPT-4.1 mini, GPT-5.4 nano and Mistral Medium 3 are proprietary and only available through APIs and apps.
Which is newer?
GPT-5.4 nano is the newest, released Mar 17, 2026. Mistral Medium 3 came out May 7, 2025; GPT-4.1 mini came out Apr 14, 2025. Knowledge cutoff: GPT-4.1 mini Apr 2024, GPT-5.4 nano Aug 31, 2025, Mistral Medium 3 May 2025.
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.
Related comparisons
- GPT-4.1 mini vs QwQ 32BAlibaba (Qwen) · ECI 137.6
- GPT-4.1 mini vs DeepSeek V3 0324DeepSeek · ECI 135.9
- GPT-4.1 mini vs Llama 4 Maverick 17B InstructMeta · ECI 132.2
- GPT-5.4 nano vs MiniMax-M2.7MiniMax · ECI 145.9
- GPT-5.4 nano vs Qwen3.6 35B-A3BAlibaba (Qwen) · ECI 143.9
- GPT-5.4 nano vs DeepSeek V3.2DeepSeek · ECI 146.3
