PricingDeepSeek1mo ago
DeepSeek
DeepSeek-V3 is a 685B parameter Mixture-of-Experts model that achieves GPT-4 level performance at significantly lower cost. Activates 37B parameters per token.
Running this yourself: likely needs a high-memory cloud gpu.
Current rates are not verified. Missing pricing does not mean free usage.
No current subscription pricing is tracked for this model.
Confirm this specific model, usage limits, and billing terms with the provider. A subscription does not automatically include API credits.
No login needed to compare. Prices are in USD; provider charges are separate from AI Market Cap plans. Context length, caching, tools, taxes, and regional terms can change the final cost. Open weights do not mean free hosting.
70.2
Quality Score
1334
Arena ELO
685B
Parameters
128K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
21 of 22 public signals
Sign in to join the discussion
1.0M
Downloads
4.2K
Likes
Dec 2024
Released
5/5 signals
4/4 signals
5/5 signals
4/4 signals
3/4 signals
Parameters
671B
Training compute
3.3e24 FLOP
Dataset scale
14.8T units
Base model
Not reported
Source-reported access: Open weights (restricted use) · Confident confidence
Gaps we are still tracking
Pricing
1
Benchmarks
19
Open Source
1
Research
2
General
1
Recent launch, pricing, benchmark, and API signals linked to this model or its provider.
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
SWE-Bench Verified resolved rate 60.0
View sourceLiveCodeBench pass@1 49.6 across 1055 tasks
View sourcelanguage: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
View sourceWe introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.
We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical and coding reasoning performance approaches that of frontier open models. It is the second open-weight LLM, after DeepSeekV3.2-Speciale-671B-A37B, to achieve Gold Medal-level performance in the 2025 International Mathematical Olympiad (IMO), the International Olympiad in Informatics (IOI), and the ICPC World Finals, demonstrating remarkably high intelligence density with 20x fewer parameters. In contrast to Nemotron-Cascade 1, the key technical advancements are as follows. After SFT on a meticulously curated dataset, we substantially expand Cascade RL to cover a much broader spectrum of reasoning and agentic domains. Furthermore, we introduce multi-domain on-policy distillation from the strongest intermediate teacher models for each domain throughout the Cascade RL process, allowing us to efficiently recover benchmark regressions and sustain strong performance gains along the way. We release the collection of model checkpoint and training data.
DeepSeek-V3 is now available through local Ollama runtime. 160K context window listed. A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
SWE-Bench Verified resolved rate 60.0
LiveCodeBench pass@1 49.6 across 1055 tasks
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6
language: 0.5 | coding: 0.3 | instruction_following: 1.0 | Overall: 0.6