DeepSeek R1 0528 vs Gemini 2.5 Flash vs Kimi K2 Instruct 0905
Gemini 2.5 Flash comes out ahead, 68 to 41 and 38 on our weighted score, and it is the cheaper option too.
DeepSeekDeepSeek R1 0528
41/100- ECI141.2
- Price$0.512 / $2.19
- Context164K
- Our pick
GoogleGemini 2.5 Flash
68/100- ECI140.6
- Price$0.30 / $2.50
- Context1.05M
Moonshot AIKimi K2 Instruct 0905
38/100- ECI—
- Price$0.60 / $2.50
- Context262K
Gemini 2.5 Flash is our pick
Gemini 2.5 Flash is the better all-round choice, scoring 68/100 against DeepSeek R1 0528 (41) and Kimi K2 Instruct 0905 (38). It leads on price, inputs & features and context window. 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 priceGemini 2.5 FlashGemini 2.5 Flash $0.85 · DeepSeek R1 0528 $0.932 · Kimi K2 Instruct 0905 $1.07 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 FlashGemini 2.5 Flash 1,048,576 · Kimi K2 Instruct 0905 262,144 · DeepSeek R1 0528 163,840 tokens
- Widest inputsGemini 2.5 FlashDeepSeek R1 0528: Text · Gemini 2.5 Flash: Text, Images, PDFs, Audio, Video · Kimi K2 Instruct 0905: Text
- Self-hostingDeepSeek R1 0528 and Kimi K2 Instruct 0905Publishes downloadable weights (MIT and Modified MIT)
| Measure | Weight | DeepSeek R1 0528 | Gemini 2.5 Flash | Kimi K2 Instruct 0905 |
|---|---|---|---|---|
| Price | 50% | 49 | 51 | 46 |
| Inputs & features | 30% | 35 | 100 | 25 |
| Context window | 20% | 28 | 61 | 37 |
| Overall | 100% | 41/100 | 68/100 | 38/100 |
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 | DeepSeek R1 0528DeepSeek | Gemini 2.5 FlashGoogle | Kimi K2 Instruct 0905Moonshot AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.2 (best) | 140.6 | — |
| ECI rank | #108 of 165 (best) | #110 of 165 | — |
| GPQA DiamondGraduate-level science questions | 76.3% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 66.4% | — | — |
| Price per million tokens | |||
| Input | $0.512 | $0.30 (best) | $0.60 |
| Output | $2.19 (best) | $2.50 | $2.50 |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $0.932 | $0.85 (best) | $1.07 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 16 providers | Official Google API | Median of 12 providers |
| Limits | |||
| Context window | 163,840 tokens | 1,048,576 tokens (best) | 262,144 tokens |
| Max output | 32,768 tokens | 65,536 tokens | 98,304 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenMIT | Proprietary | OpenModified MIT |
| API model ID | — | gemini-2.5-flash | — |
| API providers | 16 | 32 (best) | 13 |
| Released | May 28, 2025 | Jun 17, 2025 | Sep 5, 2025 |
| Knowledge cutoff | — | Jan 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek R1 0528$9.50
- Gemini 2.5 Flash$8.00
- Kimi K2 Instruct 0905$11.00
Which should you choose?
Which is better: DeepSeek R1 0528, Gemini 2.5 Flash or Kimi K2 Instruct 0905?
Gemini 2.5 Flash is the better all-round choice, scoring 68/100 against DeepSeek R1 0528 (41) and Kimi K2 Instruct 0905 (38). It leads on price, inputs & features and context window. 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, DeepSeek R1 0528, Gemini 2.5 Flash or Kimi K2 Instruct 0905?
Gemini 2.5 Flash is cheaper at $0.30 input / $2.50 output per million tokens (official Google API price). DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers); Kimi K2 Instruct 0905 costs $0.60 input / $2.50 output per million tokens (median across 12 API providers). At a typical mix of three input tokens to one output token, that is $0.85 per million tokens for Gemini 2.5 Flash versus $0.932 for DeepSeek R1 0528 (1.1× as much) and $1.07 for Kimi K2 Instruct 0905 (1.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek R1 0528 has an ECI of 141.2, Gemini 2.5 Flash has an ECI of 140.6 and Kimi K2 Instruct 0905 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek R1 0528, Gemini 2.5 Flash and Kimi K2 Instruct 0905 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 has the largest context window at 1,048,576 tokens, against 262,144 for Kimi K2 Instruct 0905 and 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, Gemini 2.5 Flash up to 65,536, Kimi K2 Instruct 0905 up to 98,304 tokens.
Which can read images, PDFs, audio or video?
DeepSeek R1 0528 accepts text; Gemini 2.5 Flash accepts text, images, PDFs, audio and video; Kimi K2 Instruct 0905 accepts text. Gemini 2.5 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek R1 0528 and Kimi K2 Instruct 0905 publishes its weights (MIT and Modified MIT) and can be self-hosted; Gemini 2.5 Flash is proprietary.
Which is newer?
Kimi K2 Instruct 0905 is the newest, released Sep 5, 2025. Gemini 2.5 Flash came out Jun 17, 2025; DeepSeek R1 0528 came out May 28, 2025. Knowledge cutoff: Gemini 2.5 Flash Jan 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 Nov 2, 2026.
Related comparisons
- DeepSeek R1 0528 vs Kimi K2 InstructMoonshot AI · ECI 139.9
- DeepSeek R1 0528 vs Qwen3 235B-A22B Thinking 2507Alibaba (Qwen) · ECI 143.8
- DeepSeek R1 0528 vs GLM-4.7Z.ai (Zhipu) · ECI 143.7
- Gemini 2.5 Flash vs Kimi K2 InstructMoonshot AI · ECI 139.9
- Gemini 2.5 Flash vs Qwen3 235B-A22B Thinking 2507Alibaba (Qwen) · ECI 143.8
- Gemini 2.5 Flash vs GPT-5 MiniOpenAI · ECI 145.4
