DeepSeek V3 Turbo vs Qwen 2 VL 72B Instruct
DeepSeek V3 Turbo is 1.1× cheaper for input tokens: DeepSeek V3 Turbo costs $0.40 per M and Qwen 2 VL 72B Instruct costs $0.45 per M. Qwen 2 VL 72B Instruct is 2.9× cheaper for output tokens: DeepSeek V3 Turbo costs $1.30 per M and Qwen 2 VL 72B Instruct costs $0.45 per M. DeepSeek V3 Turbo reads more: DeepSeek V3 Turbo takes up to 64,000 tokens of context and Qwen 2 VL 72B Instruct up to 32,768. DeepSeek V3 Turbo accepts text; Qwen 2 VL 72B Instruct accepts image, text.
| DeepSeek V3 Turbo | Qwen 2 VL 72B Instruct | |
|---|---|---|
| Model id | deepseek/deepseek-v3-turbo | qwen/qwen-2-vl-72b-instruct |
| Input | $0.40 per M | $0.45 per M |
| Output | $1.30 per M | $0.45 per M |
| Context length | 64,000 tokens | 32,768 tokens |
| Accepts | text | image, text |
| Produces | text | text |
| Served by | novita | novita |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.