Reasoning Tools JSON Open weights

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

deepseek/deepseek-v4.1-flash-1017 2026-10-17 1M context $0.15/M input $0.6/M output
32 providers
Reasoning Tools JSON Open weights

DeepSeek V4.1 Flash model for reasoning and agentic coding

deepseek/deepseek-v4.1-flash 2026-09-10 1M context $0.02/M input $1/M output
70 providers
Reasoning Tools JSON

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen3.8-flash 2026-08-26 1M context $0.15/M input $0.47/M output
31 providers
Reasoning Tools JSON

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

alibaba/qwen3.8-max 2026-08-03 1M context $2/M input $6/M output
33 providers
Reasoning Tools

Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows

alibaba/qwen3.8-max-preview 2026-07-19 1M context $0.338/M input $1.014/M output
7 providers
Reasoning Tools

Multimodal Qwen workhorse for long-context agents, visual inputs, and coding

alibaba/qwen3.7-plus 2026-06-02 1M context $0.4/M input $1.6/M output
30 providers
Reasoning Tools JSON

Qwen vision-language model for visual reasoning, documents, and agent tasks

alibaba/qwen3.6-flash 2026-04-27 1M context $0.25/M input $1.5/M output
23 providers
Reasoning Tools

Earlier Qwen multimodal workhorse for million-token agent and document tasks

alibaba/qwen3.6-plus 2026-04-02 1M context $0.5/M input $3/M output
25 providers