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. ERNIE 4.5 21B A3B ThinkingBaiduRemove
  2. DeepSeek V4.1 Flash 1017DeepSeekRemove
ernie-4.5-21b-a3b-thinking vs deepseek-v4.1-flash-1017
AttributeERNIE 4.5 21B A3B Thinkingernie-4.5-21b-a3b-thinkingDeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017
Pricing
Input$0.035 / 1M$0.10 / 1M
Output$0.14 / 1M$0.50 / 1M
Cache Write (5m)$0.035 / 1M$0.10 / 1M
Cache Write (1h)$0.035 / 1M$0.10 / 1M
Cache Read$0.035 / 1M$0.10 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context131.1K1M
Max outputN/AN/A
Capabilities
VisionYesYes
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderBaiduDeepSeek
Categorychatchat
Charge typePay As You GoPay As You Go
Released——
Description
SummaryERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model focused on deeper, higher-quality reasoning. It's tuned to perform strongly on logic, math, science, coding, text generation, and advanced academic benchmarks, delivering top-tier capability with efficient compute usage.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.