DeepSeek V4 Pro vs o4-mini-deep-research vs Gemini Robotics-ER 1.6 Preview
Gemini Robotics-ER 1.6 Preview comes out ahead, 46 to 39 and 37 on our weighted score, and it is the cheaper option too.
DeepSeekDeepSeek V4 Pro
39/100- ECI—
- Price$1.60 / $3.30
- Context1M
OpenAIo4-mini-deep-research
37/100- ECI—
- Price$1.80 / $7.20
- Context200K
- Our pick
GoogleGemini Robotics-ER 1.6 Preview
46/100- ECI—
- Price$1.00 / $5.00
- Context131K
Gemini Robotics-ER 1.6 Preview is our pick
Gemini Robotics-ER 1.6 Preview is the better all-round choice, scoring 46/100 against DeepSeek V4 Pro (39) and o4-mini-deep-research (37). It leads on inputs & features. DeepSeek V4 Pro wins on 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 Robotics-ER 1.6 PreviewGemini Robotics-ER 1.6 Preview $2.00 · DeepSeek V4 Pro $2.03 · o4-mini-deep-research $3.15 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 ProDeepSeek V4 Pro 1,000,000 · o4-mini-deep-research 200,000 · Gemini Robotics-ER 1.6 Preview 131,072 tokens
- Widest inputsGemini Robotics-ER 1.6 PreviewDeepSeek V4 Pro: Text · o4-mini-deep-research: Text, Images · Gemini Robotics-ER 1.6 Preview: Text, Images, Audio, Video
- Self-hostingDeepSeek V4 ProPublishes downloadable weights
| Measure | Weight | DeepSeek V4 Pro | o4-mini-deep-research | Gemini Robotics-ER 1.6 Preview |
|---|---|---|---|---|
| Price | 50% | 34 | 25 | 34 |
| Inputs & features | 30% | 35 | 60 | 80 |
| Context window | 20% | 60 | 32 | 25 |
| Overall | 100% | 39/100 | 37/100 | 46/100 |
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 V4 ProDeepSeek | o4-mini-deep-researchOpenAI | Gemini Robotics-ER 1.6 PreviewGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.60 | $1.80 | $1.00 (best) |
| Output | $3.30 (best) | $7.20 | $5.00 |
| Cached input | — | — | — |
| Blended (3:1) | $2.03 | $3.15 | $2.00 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 56 providers | Median of 1 providers | Median of 1 providers |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 200,000 tokens | 131,072 tokens |
| Max output | 384,000 tokens (best) | 100,000 tokens | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | — | — | — |
| API providers | 58 (best) | 1 | 1 |
| Released | Apr 24, 2026 | Jun 26, 2025 | Apr 14, 2026 |
| Knowledge cutoff | May 2025 | May 2024 | 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 V4 Pro$22.60
- o4-mini-deep-research$32.40
- Gemini Robotics-ER 1.6 Preview$20.00
Which should you choose?
Which is better: DeepSeek V4 Pro, o4-mini-deep-research or Gemini Robotics-ER 1.6 Preview?
Gemini Robotics-ER 1.6 Preview is the better all-round choice, scoring 46/100 against DeepSeek V4 Pro (39) and o4-mini-deep-research (37). It leads on inputs & features. DeepSeek V4 Pro wins on 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 V4 Pro, o4-mini-deep-research or Gemini Robotics-ER 1.6 Preview?
Gemini Robotics-ER 1.6 Preview is cheaper at $1.00 input / $5.00 output per million tokens (median across 1 API provider). DeepSeek V4 Pro costs $1.60 input / $3.30 output per million tokens (median across 56 API providers); o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $2.00 per million tokens for Gemini Robotics-ER 1.6 Preview versus $2.03 for DeepSeek V4 Pro (1× as much) and $3.15 for o4-mini-deep-research (1.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek V4 Pro has not been scored yet, o4-mini-deep-research has not been scored yet and Gemini Robotics-ER 1.6 Preview has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek V4 Pro, o4-mini-deep-research and Gemini Robotics-ER 1.6 Preview 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?
DeepSeek V4 Pro has the largest context window at 1,000,000 tokens, against 200,000 for o4-mini-deep-research and 131,072 for Gemini Robotics-ER 1.6 Preview. Maximum output per response: DeepSeek V4 Pro up to 384,000, o4-mini-deep-research up to 100,000, Gemini Robotics-ER 1.6 Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro accepts text; o4-mini-deep-research accepts text and images; Gemini Robotics-ER 1.6 Preview accepts text, images, audio and video. Gemini Robotics-ER 1.6 Preview handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro publishes its weights and can be self-hosted; o4-mini-deep-research and Gemini Robotics-ER 1.6 Preview is proprietary.
Which is newer?
DeepSeek V4 Pro is the newest, released Apr 24, 2026. Gemini Robotics-ER 1.6 Preview came out Apr 14, 2026; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: DeepSeek V4 Pro May 2025, o4-mini-deep-research May 2024, Gemini Robotics-ER 1.6 Preview 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.
