GPT-4.1 mini vs Grok 4.3 vs Mistral Medium 3
Grok 4.3 comes out ahead, 67 to 60 and 53 on our weighted score, though GPT-4.1 mini is 2.2× cheaper per token.
OpenAIGPT-4.1 mini
60/100- ECI135.0
- Price$0.40 / $1.60
- Context1.05M
- Our pick
xAIGrok 4.3
67/100- ECI149.2
- Price$1.25 / $2.50
- Context1M
Mistral AIMistral Medium 3
53/100- ECI134.1
- Price$0.40 / $2.00
- Context131K
Grok 4.3 is our pick
Grok 4.3 is the better all-round choice, scoring 67/100 against GPT-4.1 mini (60) and Mistral Medium 3 (53). It leads on capability and inputs & features. GPT-4.1 mini wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGrok 4.3Capabilities Index (ECI): Grok 4.3 149.2 · GPT-4.1 mini 135.0 · Mistral Medium 3 134.1
- Lowest priceGPT-4.1 miniGPT-4.1 mini $0.70 · Mistral Medium 3 $0.80 · Grok 4.3 $1.56 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · Grok 4.3 1,000,000 · Mistral Medium 3 131,072 tokens
- Widest inputsGPT-4.1 mini and Grok 4.3GPT-4.1 mini: Text, Images, PDFs · Grok 4.3: Text, Images, PDFs · Mistral Medium 3: Text, Images
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | GPT-4.1 mini | Grok 4.3 | Mistral Medium 3 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 59 | 77 | 58 |
| Price | 25% | 57 | 41 | 54 |
| Inputs & features | 15% | 70 | 80 | 50 |
| Context window | 10% | 61 | 60 | 24 |
| Overall | 100% | 60/100 | 67/100 | 53/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-4.1 miniOpenAI | Grok 4.3xAI | Mistral Medium 3Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 135.0 | 149.2 (best) | 134.1 |
| ECI rank | #115 of 148 | #55 of 148 (best) | #117 of 148 |
| GPQA DiamondGraduate-level science questions | 65.9% | 88.8% (best) | 59.5% |
| FrontierMath Tiers 1–3Research-level mathematics | 6.7% | 42.8% (best) | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 44.7% | 93.3% (best) | 32.2% |
| SimpleQA VerifiedShort factual questions | 12.7% | 33.2% (best) | — |
| Price per million tokens | |||
| Input | $0.40 (best) | $1.25 | $0.40 (best) |
| Output | $1.60 (best) | $2.50 | $2.00 |
| Cached input | $0.10 (best) | $0.20 | — |
| Blended (3:1) | $0.70 (best) | $1.56 | $0.80 |
| Long-context rate | Same rate | Over 200K: $2.50 / $5.00 | Same rate |
| Price source | Official OpenAI API | Official xAI API | Official Mistral API |
| Limits | |||
| Context window | 1,047,576 tokens (best) | 1,000,000 tokens | 131,072 tokens |
| Max output | 32,768 tokens | 30,000 tokens | 131,072 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yeslow · medium · high | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-4.1-mini | grok-4.3 | mistral-medium-2505 |
| API providers | 24 | 27 (best) | 5 |
| Released | Apr 14, 2025 | Apr 17, 2026 | May 7, 2025 |
| Knowledge cutoff | Apr 2024 | — | 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
- Grok 4.3$17.50
- Mistral Medium 3$8.00
Which should you choose?
Which is better: GPT-4.1 mini, Grok 4.3 or Mistral Medium 3?
Grok 4.3 is the better all-round choice, scoring 67/100 against GPT-4.1 mini (60) and Mistral Medium 3 (53). It leads on capability and inputs & features. GPT-4.1 mini wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-4.1 mini, Grok 4.3 or Mistral Medium 3?
GPT-4.1 mini is cheaper at $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); Grok 4.3 costs $1.25 input / $2.50 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.70 per million tokens for GPT-4.1 mini versus $0.80 for Mistral Medium 3 (1.1× as much) and $1.56 for Grok 4.3 (2.2× as much).
Which scores higher on benchmarks?
Grok 4.3 scores higher on the Capabilities Index (ECI): Grok 4.3 149.2 (#55 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 (147.6–150.8 vs 131.2–136.6), so the gap is a real one. On individual benchmarks: GPQA Diamond — Grok 4.3 88.8%, GPT-4.1 mini 65.9%, Mistral Medium 3 59.5%; OTIS Mock AIME 2024–2025 — Grok 4.3 93.3%, 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, Grok 4.3 and Mistral Medium 3 yet, so there is no like-for-like coding score. On overall capability, Grok 4.3 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 1,000,000 for Grok 4.3 and 131,072 for Mistral Medium 3. Maximum output per response: GPT-4.1 mini up to 32,768, Grok 4.3 up to 30,000, 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; Grok 4.3 accepts text, images and PDFs; 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, Grok 4.3 and Mistral Medium 3 are proprietary and only available through APIs and apps.
Which is newer?
Grok 4.3 is the newest, released Apr 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, 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.
