Model creator
DeepSeek
Every DeepSeek model in the BenchSift catalogue, with its scores, ranks, prices and capabilities as the sources publish them.
- Models
- 36
- 48 configurations, reasoning levels included
- Open weights
- 36
- 36 of 36 models
- Latest release
- Oct 17, 2026
- DeepSeek V4.1 Flash 1017 (High) · First dated model: Nov 29, 2023
- Median price
- $0.521
- $0.142 to $2.50 per million tokens, across 18 priced models
Models
36Reasoning levels are folded into one entry. The rank is the whole catalogue's: sorting does not change it.
- DeepSeek V4 Flash Vision (Max)34.8#81 of 782$0.66141 t/s
Text · Reasoning · Open weights · Aug 21, 2026 · $0.66 · 141 t/s
- DeepSeek V4 Flash 0731 (Max)34.3#89 of 782$0.175129 t/s
Text · Reasoning · Open weights · Jul 31, 2026 · $0.175 · 129 t/s
- DeepSeek V4.1 Flash 101732.6#103 of 782$0.525152 t/s
Text · Reasoning · Open weights · 3 configurations · Oct 17, 2026 · $0.525 · 152 t/s
- DeepSeek V4 Pro 042430.4#123 of 782$1.7771.9 t/s
Text · Reasoning · Open weights · 3 configurations · Apr 24, 2026 · $1.77 · 71.9 t/s
- DeepSeek V4.1 Flash28.6#141 of 782$0.517203 t/s
Text · Reasoning · Open weights · 2 configurations · Sep 10, 2026 · $0.517 · 203 t/s
- DeepSeek V4 Flash 042024.2#198 of 782$0.14258.3 t/s
Text · Reasoning · Open weights · 3 configurations · Apr 24, 2026 · $0.142 · 58.3 t/s
- DeepSeek V4 Pro 081323.1#214 of 782$1.9875 t/s
Text · Reasoning · Open weights · 2 configurations · Aug 13, 2026 · $1.98 · 75 t/s
- DeepSeek V3.221.5#239 of 782$0.31546.3 t/s
Text · Reasoning · Open weights · 2 configurations · Dec 1, 2025 · $0.315 · 46.3 t/s
- DeepSeek V3.1 Terminus14.8#332 of 782$0.45371.5 t/s
Text · Reasoning · Open weights · 2 configurations · Sep 22, 2025 · $0.453 · 71.5 t/s
- DeepSeek V3.2 Speciale14.5#336 of 782——
Text · Reasoning · Open weights · Dec 1, 2025
- DeepSeek V3.2 Exp13.9#346 of 782$0.315—
Text · Reasoning · Open weights · 2 configurations · Sep 29, 2025 · $0.315
- DeepSeek V3.113.7#349 of 782$0.8470.4 t/s
Text · Reasoning · Open weights · 2 configurations · Aug 21, 2025 · $0.84 · 70.4 t/s
- DeepSeek R1 0528 (May '25)13.1#363 of 782$2.0833.1 t/s
Text · Reasoning · Open weights · May 28, 2025 · $2.08 · 33.1 t/s
- R1 052813.1#363 of 782$0.913—
Text · Reasoning · Open weights · May 28, 2025 · $0.913
- DeepSeek R1 (Jan '25)11.4#410 of 782$2.50129 t/s
Text · Reasoning · Open weights · Jan 20, 2025 · $2.50 · 129 t/s
- DeepSeek V3 03249.7#456 of 782$0.405125 t/s
Text · Open weights · Mar 25, 2025 · $0.405 · 125 t/s
- DeepSeek V3 (Dec '24)8.5#509 of 782$0.46375.5 t/s
Text · Open weights · Dec 26, 2024 · $0.463 · 75.5 t/s
- DeepSeek R1 Distill Qwen 32B8.4#511 of 782——
Text · Reasoning · Open weights · Jan 20, 2025
- DeepSeek R1 0528 Qwen3 8B8.1#525 of 782——
Text · Reasoning · Open weights · May 29, 2025
- DeepSeek R1 Distill Llama 70B7.9#527 of 782$0.80—
Text · Reasoning · Open weights · Jan 20, 2025 · $0.80
- DeepSeek R1 Distill Qwen 14B7.8#533 of 782——
Text · Reasoning · Open weights · Jan 20, 2025
- DeepSeek-V2.5 (Dec '24)6.6#622 of 782——
Text · Open weights · Dec 10, 2024
- DeepSeek-V2.56.6#622 of 782——
Text · Open weights · Sep 6, 2024
- DeepSeek R1 Distill Llama 8B6.5#631 of 782——
Text · Reasoning · Open weights · Jan 20, 2025
- DeepSeek-Coder-V26.0#660 of 782——
Text · Open weights · Jun 17, 2024
- DeepSeek R1 Distill Qwen 1.5B5.5#698 of 782——
Text · Reasoning · Open weights · Jan 20, 2025
- DeepSeek-V2-Chat5.5#698 of 782——
Text · Open weights · May 6, 2024
- DeepSeek Coder V2 Lite Instruct5.3#718 of 782——
Text · Open weights · Jun 17, 2024
- DeepSeek LLM 67B Chat (V1)5.3#718 of 782——
Text · Open weights · Nov 29, 2023
- DeepSeek V4 Flash Vision Exp (batch)—$0.165—
Text · Reasoning · Open weights · Aug 21, 2026 · $0.165
- DeepSeek V4 Flash 0423———
Text · Reasoning · Open weights · Apr 23, 2026
- DeepSeek V4 Pro 0423———
Text · Reasoning · Open weights · Apr 23, 2026
- DeepSeek OCR 2———
Text · Open weights · Jan 27, 2026
- DeepSeek Chat———
Text · Open weights · Dec 1, 2025
- DeepSeek Reasoner———
Text · Reasoning · Open weights · Dec 1, 2025
- Janus Pro————
Image · Open weights
Where these figures come from
Each catalogue model is tied to its creator by the identity Artificial Analysis publishes, or OpenRouter's and Models.dev's for models it does not track. Counts fold the reasoning levels of one model together. Ranks compare each measure with every measured model in the catalogue, configurations included, as model pages do. The price is the published blended price (3 input tokens to 1 output token).
Figures computed by BenchSift from the catalogue: Artificial Analysis, OpenRouter, Models.dev and Hugging Face. A value no model carries is not shown.
Data retrieved on Nov 12, 2026.