DeepSeek v4 Pro 0813 byNara
deepseek-v4-pro-0813-bynaraDeepSeek-V4-Pro is DeepSeek's flagship open-weights reasoning model in the V4 generation (the successor to V3/R1), tuned for multi-step reasoning, mathematics and coding rather than the Flash tier's latency. The '0813 byNara' build is a dated checkpoint of that Pro model served via byNara's cloud hosting.
Best for
Characteristics
Modalities
Use cases
Anthropic
Yes
Chat Completions
Responses Api
Yes
Provider
DeepSeek
Context Window
1M
Available Access
Prices shown per 1M tokens.
Input
Rp. 1.848
$0.1 USD
Output
Rp. 3.696
$0.21 USD
Cache
Rp. 154
$0.01 USD
All prices are estimates and subject to change.
Similar Models
Related models selected by the catalog administrator.
deepseek-v4-proDeepSeek's V4 Pro model, the stronger, reasoning-optimized flagship tier of the DeepSeek-V4 generation aimed at complex problem-solving, coding and agentic tasks, with a 1M-token context.
deepseek-v4-pro-alibabaDeepSeek-V4-Pro is DeepSeek's premium open-weights reasoning and coding model from the V4 family (following DeepSeek-V3/R1), offering stronger multi-step reasoning and agentic capabilities than the lighter Flash tier. This 'Alibaba' variant is the same model served via Alibaba Cloud's hosting platform.
glm-5.2GLM-5.2 is Z.ai's (Zhipu AI) flagship general-purpose LLM and part of the GLM-5 family, positioned as a strong all-round model for coding and agentic workflows across tools like Claude Code and Codex. It sits just below GLM-5.3 in the family's progression of intensive-reinforcement-learning-tuned models.