Models
One name per model, however many providers serve it.
DeepSeek: DeepSeek V4.1 Flash 1017
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningDeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
deepseek/deepseek-v4.1-flash-1017Oct 17, 20261M context109,312 Toman/M input tokens433,832 Toman/M output tokensDeepSeek: DeepSeek Pro Latest
Accepts- Text
Creates- Text
ToolsJSONReasoningThis model always redirects to the latest model in the DeepSeek Pro family.
~deepseek/deepseek-pro-latestSep 14, 20261M context44,408 Toman/M input tokens2,883,104 Toman/M output tokensDeepSeek: DeepSeek Flash Latest
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningThis model always redirects to the latest model in the DeepSeek Flash family.
~deepseek/deepseek-flash-latestSep 14, 20261M context13,664 Toman/M input tokens181,048 Toman/M output tokensDeepSeek: DeepSeek V4.1 Flash
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
deepseek/deepseek-v4.1-flashSep 10, 20261M context20,496 Toman/M input tokens75,152 Toman/M output tokensDeepSeek: DeepSeek V4 Flash Vision Exp
Accepts- Text
- Image
Creates- Text
ToolsJSONReasoningDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents…
deepseek/deepseek-v4-flash-vision-expAug 21, 20261M context78,568 Toman/M input tokens235,704 Toman/M output tokensDeepSeek: DeepSeek V4 Pro 0813
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
deepseek/deepseek-v4-pro-0813Aug 12, 20261M context478,240 Toman/M input tokens1,427,888 Toman/M output tokensDeepSeek: DeepSeek V4 Flash Latest
Accepts- Text
Creates- Text
ToolsJSONReasoningThis model always redirects to the latest model in the DeepSeek V4 Flash family.
~deepseek/deepseek-v4-flash-latestAug 1, 20261M context17,080 Toman/M input tokens47,824 Toman/M output tokensDeepSeek: DeepSeek V4 Flash 0731
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
deepseek/deepseek-v4-flash-0731Jul 31, 20261M context17,080 Toman/M input tokens109,312 Toman/M output tokensDeepSeek: DeepSeek V4 Pro 0423
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.
deepseek/deepseek-v4-proApr 24, 20261M context324,520 Toman/M input tokens543,144 Toman/M output tokensDeepSeek: DeepSeek V4 Flash 0423
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
deepseek/deepseek-v4-flashApr 24, 20261M context34,160 Toman/M input tokens64,904 Toman/M output tokensDeepSeek: DeepSeek V3.2
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.
deepseek/deepseek-v3.2Dec 1, 2025164K context95,648 Toman/M input tokens140,056 Toman/M output tokensDeepSeek: DeepSeek V3.2 Exp
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
deepseek/deepseek-v3.2-expSep 29, 2025164K context99,064 Toman/M input tokens150,304 Toman/M output tokensDeepSeek: DeepSeek V3.1 Terminus
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's…
deepseek/deepseek-v3.1-terminusSep 22, 2025164K context99,064 Toman/M input tokens362,096 Toman/M output tokensDeepSeek: DeepSeek V3.1
Accepts- Text
Creates- Text
ToolsJSONReasoningDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates.
deepseek/deepseek-chat-v3.1Aug 21, 2025164K context92,232 Toman/M input tokens345,016 Toman/M output tokensDeepSeek: DeepSeek R1 0528
Accepts- Text
Creates- Text
ToolsJSONReasoningMay 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens.
deepseek/deepseek-r1-0528May 28, 2025164K context208,376 Toman/M input tokens826,672 Toman/M output tokensDeepSeek: DeepSeek V3 0324
Accepts- Text
Creates- Text
ToolsJSONDeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
deepseek/deepseek-chat-v3-0324Mar 24, 2025164K context92,232 Toman/M input tokens362,096 Toman/M output tokensDeepSeek: DeepSeek V3
Accepts- Text
Creates- Text
ToolsJSONDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
deepseek/deepseek-chatDec 26, 2024164K context95,648 Toman/M input tokens372,344 Toman/M output tokens
17 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

