Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | deepseekDeepSeek: DeepSeek V4.1 FlashRemove × |
|---|---|
| What’s different | Causal encoder-decoder activates 8B parameters for input and 16B for output, reducing the compute needed for long inputs. |
| Date | Sep 10, 2026Released |
API prices USD · provider configuration shown below | |
| Listed rate | $0.0648 in / $0.144 out/ 1M tokensOpenInference · via OpenRouter · all routes ↗open-inference/fp4 · quantization=fp4 |
| Provider endpoints | 45 endpoints → |
Benchmarks Each result retains its evaluation configuration | |
| AA Intelligence ↗4.3.2 | 39.46 ↗Effort: max · MaxIndependent result |
| AA-Briefcase ↗1.1 | 1,420.2 ↗Effort: max · MaxIndependent result |
| GDPval-AA ↗2.1 | 1,600 ↗Effort: max · MaxIndependent result |
| AutomationBench-AA ↗AA Index 4.3.2 collection | 68.89% ↗Effort: max · MaxIndependent result |
| Terminal-Bench 4.0 · AA ↗ | 26.77% ↗Effort: max · MaxHarness unreportedIndependent result |
| SciCode ↗AA Index 4.3.2 collection | 51.85% ↗AA · Under reviewEffort: max · MaxIndependent result |
| Humanity’s Last Exam ↗AA Index 4.3.2 collection | 39.25% ↗Effort: max · MaxIndependent result |
| GDP.pdf ↗AA Index 4.3.2 collection | 12.8% ↗Effort: max · MaxIndependent result |
| CritPt ↗AA Index 4.3.2 collection | 14.29% ↗AA · Under reviewEffort: max · MaxIndependent result |
| AA-Omniscience ↗AA Index 4.3.2 collection | -5.3 ↗Effort: max · MaxIndependent result |
| AA-LCR ↗1.1 | 84% ↗Effort: max · MaxIndependent result |
| LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 78.04% ↗Effort: max · single run · equal mean of 7 suitesIndependent result |
| LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 79.2% ↗Effort: max · single runIndependent result |
| LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 86.8% ↗Effort: max · single runIndependent result |
| LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 84% ↗Effort: max · single runIndependent result |
| LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 90.2% ↗Effort: max · single runIndependent result |
| LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 40.1% ↗Effort: max · single runIndependent result |
| LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 79.3% ↗Effort: max · single runIndependent result |
| LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02) | 86.7% ↗Effort: max · single runIndependent result |
Specifications | |
| Context window | 1M |
| Max output | 943.7K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Image input | Supported |
| Reasoning | Supported |
| Prompt caching | Supported |
| Open weights | Supported |