Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. MiniMax M3MiniMaxRemove
  2. DeepSeek V4.1 Flash 1017DeepSeekRemove
  3. Muse WonderMetaRemove
  4. Muse Spark OpenMetaRemove

4 is the maximum. Remove one to add another.

minimax-m3 vs deepseek-v4.1-flash-1017 vs muse-wonder vs muse-spark-open
AttributeMiniMax M3minimax-m3DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017Muse Wondermuse-wonderMuse Spark Openmuse-spark-open
Pricing
Input$0.30 / 1M$0.10 / 1M$4.00 / 1M$1.25 / 1M
Output$1.20 / 1M$0.50 / 1M$20.00 / 1M$4.25 / 1M
Cache Write (5m)$0.30 / 1M$0.10 / 1M$4.00 / 1M$1.25 / 1M
Cache Write (1h)$0.30 / 1M$0.10 / 1M$4.00 / 1M$1.25 / 1M
Cache Read$0.30 / 1M$0.10 / 1M$4.00 / 1M$1.25 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M$0 / 1M
Context
Max context1M1M1M1M
Max outputN/AN/AN/AN/A
Capabilities
VisionYesYesYesYes
Function CallingYesYesYesYes
JSON ModeYesYesYesYes
StreamingYesYesYesYes
Catalogue
ProviderMiniMaxDeepSeekMetaMeta
Categorychatchatchatchat
Charge typePay As You GoPay As You GoPay As You GoPay As You Go
Released————
Description
SummaryMiniMax-M3 is a multimodal foundation model from MiniMax, supporting text, image, and video inputs with text output and a 1M-token context window. It is designed for long-horizon agentic workflows, coding, and tool-driven task execution, enabling sustained reasoning across complex tasks. Built on MiniMax Sparse Attention (MSA), the model dramatically improves long-context efficiency by replacing full attention with KV-block selection, reducing compute costs at 1M-token contexts while maintaining strong performance. Trained as a native multimodal model and optimized for multi-turn, production-style collaboration, MiniMax-M3 excels at extended, multi-step workflows rather than single-turn interactions.DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek’s cost-efficient Mixture-of-Experts (MoE) model, built on its innovative Causal Encoder-Decoder (CED) architecture. Featuring 552B total parameters with 8B activated for input and 16B for output, it combines efficient inference with native multimodal understanding through jointly trained text and visual representations. Optimized for coding, terminal and computer-use agents, and long-horizon workflows, the model introduces compressed KV caching that reduces cache memory usage to approximately one-quarter of the previous Flash generation. DeepSeek reports that it surpasses V4 Pro in performance, inference speed, and task completion time, making it well suited for cost-efficient autonomous agents, complex software engineering, and long-context analysis.Muse Wonder is Meta’s frontier multimodal reasoning model, designed for complex personal and professional agentic workflows. It supports text, image, video, audio, and PDF inputs with text output and features a 1M-token context window for sustained reasoning across long-running tasks. Optimized for autonomous execution and multi-agent orchestration, Muse Wonder can plan, delegate to subagents, coordinate parallel tool use, recover from errors, and operate browsers and applications across desktop and mobile environments. With cross-conversation context retrieval and its Active Focus training approach, it is well suited for complex software engineering, multi-file refactoring, computer use, and end-to-end workflows requiring persistence, adaptability, and minimal supervision.Muse Spark Open is an open-weight, coding-optimized model designed for agentic software engineering workflows. It delivers strong first-attempt accuracy, reliable tool calling, and deep codebase understanding, enabling effective development across real-world repositories. Optimized for autonomous coding agents, complex code navigation, and tool-driven development, Muse Spark Open is well suited for software engineering automation, debugging, code generation, and multi-step coding workflows where accuracy and reliable execution are essential.