DeepSeek V3 0324 vs GPT-4.1 mini vs Kimi K2 Thinking
Too close to call on our weighted score (GPT-4.1 mini 64, Kimi K2 Thinking 61, DeepSeek V3 0324 52). The right pick depends on what you value most.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek V3 0324
52/100- ECI135.3
- Price$0.275 / $1.12
- Context164K
OpenAI
GPT-4.1 mini
64/100- ECI134.3
- Price$0.40 / $1.60
- Context1.05M
Moonshot AI
Kimi K2 Thinking
61/100- ECI145.5
- Price$0.60 / $2.50
- Context262K
Too close to call
It is close. Our weighted score puts them within 3 points (GPT-4.1 mini 64/100, Kimi K2 Thinking 61/100, DeepSeek V3 0324 52/100), so choose by what matters most for your work: Kimi K2 Thinking for raw capability, DeepSeek V3 0324 on price and GPT-4.1 mini for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityKimi K2 ThinkingCapabilities Index (ECI): Kimi K2 Thinking 145.5 · DeepSeek V3 0324 135.3 · GPT-4.1 mini 134.3
- Lowest priceDeepSeek V3 0324DeepSeek V3 0324 $0.486 · GPT-4.1 mini $0.70 · Kimi K2 Thinking $1.07 per 1M tokens (3:1 blend)
- Longest contextGPT-4.1 miniGPT-4.1 mini 1,047,576 · Kimi K2 Thinking 262,144 · DeepSeek V3 0324 163,840 tokens
- Widest inputsGPT-4.1 miniDeepSeek V3 0324: Text · GPT-4.1 mini: Text, Images, PDFs · Kimi K2 Thinking: Text
- Self-hostingDeepSeek V3 0324 and Kimi K2 ThinkingPublishes downloadable weights
| Measure | Weight | DeepSeek V3 0324 | GPT-4.1 mini | Kimi K2 Thinking |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 63 | 62 | 73 |
| Inputs & features | 20% | 25 | 70 | 35 |
| Context window | 13% | 36 | 65 | 43 |
| Overall | 100% | 52/100 | 64/100 | 61/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 135.3 | 134.3 | 145.5 (best) |
| ECI rank | #125 of 158 | #128 of 158 | #90 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 67.6% | 65.9% | 84.2% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | 6.7% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 37.8% | 44.7% | 83.1% (best) |
| SimpleQA VerifiedShort factual questions | — | 12.7% | — |
| Price per million tokens | |||
| Input | $0.275 (best) | $0.40 | $0.60 |
| Output | $1.12 (best) | $1.60 | $2.50 |
| Cached input | — | $0.10 | — |
| Blended (3:1) | $0.486 (best) | $0.70 | $1.07 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 13 providers | Official OpenAI API | Median of 14 providers |
| Limits | |||
| Context window | 163,840 tokens | 1,047,576 tokens (best) | 262,144 tokens |
| Max output | 163,840 tokens | 32,768 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | gpt-4.1-mini | — |
| API providers | 13 | 30 (best) | 15 |
| Released | Mar 24, 2025 | Apr 14, 2025 | Nov 6, 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.
DeepSeek V3 0324$4.99
GPT-4.1 mini$7.20
Kimi K2 Thinking$11.00
Which should you choose?
Which is better: DeepSeek V3 0324, GPT-4.1 mini or Kimi K2 Thinking?
It is close. Our weighted score puts them within 3 points (GPT-4.1 mini 64/100, Kimi K2 Thinking 61/100, DeepSeek V3 0324 52/100), so choose by what matters most for your work: Kimi K2 Thinking for raw capability, DeepSeek V3 0324 on price and GPT-4.1 mini for long inputs. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek V3 0324, GPT-4.1 mini or Kimi K2 Thinking?
DeepSeek V3 0324 is cheaper at $0.275 input / $1.12 output per million tokens (median across 13 API providers). GPT-4.1 mini costs $0.40 input / $1.60 output per million tokens (official OpenAI API price); Kimi K2 Thinking costs $0.60 input / $2.50 output per million tokens (median across 14 API providers). At a typical mix of three input tokens to one output token, that is $0.486 per million tokens for DeepSeek V3 0324 versus $0.70 for GPT-4.1 mini (1.4× as much) and $1.07 for Kimi K2 Thinking (2.2× as much).
Which scores higher on benchmarks?
Kimi K2 Thinking scores higher on the Capabilities Index (ECI): Kimi K2 Thinking 145.5 (#90 of 158), DeepSeek V3 0324 135.3 (#125 of 158) and GPT-4.1 mini 134.3 (#128 of 158). Their confidence ranges do not overlap (143.7–147.3 vs 133.1–137.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — Kimi K2 Thinking 84.2%, DeepSeek V3 0324 67.6%, GPT-4.1 mini 65.9%; OTIS Mock AIME 2024–2025 — Kimi K2 Thinking 83.1%, GPT-4.1 mini 44.7%, DeepSeek V3 0324 37.8%.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V3 0324, GPT-4.1 mini and Kimi K2 Thinking yet, so there is no like-for-like coding score. On overall capability, Kimi K2 Thinking 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 262,144 for Kimi K2 Thinking and 163,840 for DeepSeek V3 0324. Maximum output per response: DeepSeek V3 0324 up to 163,840, GPT-4.1 mini up to 32,768, Kimi K2 Thinking up to 262,144 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V3 0324 accepts text; GPT-4.1 mini accepts text, images and PDFs; Kimi K2 Thinking accepts text. GPT-4.1 mini handles the widest range of inputs.
Are any of these open source?
DeepSeek V3 0324 and Kimi K2 Thinking publishes its weights and can be self-hosted; GPT-4.1 mini is proprietary.
Which is newer?
Kimi K2 Thinking is the newest, released Nov 6, 2025. GPT-4.1 mini came out Apr 14, 2025; DeepSeek V3 0324 came out Mar 24, 2025. Knowledge cutoff: GPT-4.1 mini Apr 2024, Kimi K2 Thinking Aug 2024.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.