Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
DeepSeek V3
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous version
SharkScore
#128 in Models
Why it scores 37.1
DeepSeek V3 has a SharkScore of 37.1/100, ranked #128 of 607 in Models (updated 2026-11-19).
Each part compares DeepSeek V3 with other listings in Models. Evidence covers 87% of the score's weight.
- Adoption
- 36 · 30%
- User reviews
- no data · 25%
- Maintenance
- 0 · 20%
- Trust & transparency
- 80 · 15%
- Momentum
- no data · 10%
Paying never changes this score. How ranking works · method v2026-11-18.2
RankShark review of DeepSeek V3
Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review
We were not paid for this review.
As of 2026-11-18, DeepSeek V3 is a text model listed with a 163,840-token OpenRouter context window and per-token API rates. [E2]
DeepSeek V3 is a 671B-parameter mixture-of-experts language model with 37B parameters activated per token. It handles text input and output, and can be accessed through APIs or deployed locally. [E1][E2]
Best for
- Developers who want to access a text model through an API. · model card, OpenRouter
- Teams evaluating a model for coding, math, or text tasks; the model card reports results on benchmarks in those areas. · model card
- Users seeking local deployment options through listed community software. · model card
Not for
- Users who need a model listing that supports image, audio, or video input; the OpenRouter listing specifies text input and output only. · OpenRouter
Key features
- Mixture-of-experts architecture. The vendor says DeepSeek V3 has 671B total parameters, with 37B activated for each token. · model card
- Long context. The OpenRouter listing shows a context length of 163,840 tokens; the model card lists 128K. · model card, OpenRouter
- Text input and output. The OpenRouter listing specifies text input and text output. · OpenRouter
- API access. The vendor says it provides an OpenAI-compatible API, and the OpenRouter listing includes chat completions, completions, messages, and responses endpoints. · model card, OpenRouter
- Local deployment options. The vendor lists DeepSeek-Infer Demo, SGLang, and LMDeploy for running the model locally or in cloud deployments. · model card
- Reported benchmark evaluations. The vendor reports evaluations for chat, coding, math, Chinese, and other language tasks. · model card
Pros
- The model is available through an OpenAI-compatible API and through several listed OpenRouter endpoints. · model card, OpenRouter
- The vendor lists local deployment options, including SGLang and LMDeploy. · model card
- The model card includes benchmark results across coding, math, and language tasks. · model card
Cons
- The model card lists a 128K context length, while the OpenRouter listing shows 163,840 tokens. · model card, OpenRouter
- The pricing evidence gives per-token rates, not a monthly subscription price. · OpenRouter
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.
Pricing
| Plan | Price | Limits |
|---|---|---|
| OpenRouter API (per-token rates) | $0.2574 per million input tokens; $1.0287 per million output tokens | No monthly plan limits stated. |
Checked 18 Nov 2026
- Free plan
- Not stated (checked 18 Nov 2026)
- Free trial
- Not stated (checked 18 Nov 2026)
- Trains on customer data
- Not stated (checked 18 Nov 2026)
- Data retention
- Not stated (checked 18 Nov 2026)
- Data regions
- Not stated (checked 18 Nov 2026)
- Data processing agreement
- Not stated (checked 18 Nov 2026)
- AI models used
- DeepSeek-V3 · model card, OpenRouter
- API
- The vendor says it provides an OpenAI-compatible API. The OpenRouter listing includes chat completions, completions, messages, and responses endpoints. · model card, OpenRouter
- SDKs
- Not stated (checked 18 Nov 2026)
- Webhooks
- Not stated (checked 18 Nov 2026)
- Platforms
- The vendor lists its website and API platform, plus local deployment options through DeepSeek-Infer Demo, SGLang, and LMDeploy. · model card
- Security claims
- No security certification stated (checked 18 Nov 2026)
What we measured
- Context window (OpenRouter listing) · now
- 163,840 tokens
- Price per million tokens (OpenRouter listing) · now
- $0.257 in, $1.029 out
- Package downloads · 30 days
- 1,418,977
How we tested · sources
- Hourly uptime and response-time checks of the product's URL.
- Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
- We did not sign up, pay, or use the product as a customer.
- model card: https://huggingface.co/deepseek-ai/DeepSeek-V3 · fetched 18 Nov 2026
- OpenRouter: https://openrouter.ai/deepseek/deepseek-chat · fetched 18 Nov 2026
- 18 Nov 2026: Plans or prices changed on the pricing page.
Something wrong? Report an error with a public link that shows it; corrections re-run the review.
Top alternatives to DeepSeek V3
See all- 67.1ModelOpen source
- 65.5
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
ModelOpen source - 64.7
Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
ModelOpen source - 64.3
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
ModelOpen source