October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
31 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek V4.1 Flash model for reasoning and agentic coding
70 providers
Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work
23 providers
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
42 providers
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
54 providers
Open MoE flagship with million-token context for coding and long agent runs
71 providers
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
68 providers
DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes
2 providers
Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads
4 providers
High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes
3 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
28 providers
DeepSeek chat model for instruction following, coding, and analysis
8 providers
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
5 providers
DeepSeek chat model for instruction following, coding, and analysis
10 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
13 providers
DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning
1 provider
May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning
10 providers
DeepSeek chat model for instruction following, coding, and analysis
8 providers
March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding
9 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
16 providers
R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving
1 provider
Open DeepSeek MoE chat model for coding, math, and general reasoning
10 providers
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-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 R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017 | DeepSeek |
1M | $0.15 | $0.6 | 2026-10-17 | ||
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek |
1M | $0.02 | $1 | 2026-09-10 | ||
| DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp | DeepSeek |
1M | $0.15 | $0.6 | 2026-08-21 | ||
| DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 | DeepSeek |
1M | $0.132 | $0.396 | 2026-08-13 | ||
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | DeepSeek |
1M | $0.035 | $0.07 | 2026-07-31 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
1M | $0.66 | $1.98 | 2026-04-24 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
1M | $0.15 | $0.6 | 2026-04-24 | ||
| DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro-0423 | DeepSeek |
1M | $1.32 | $3.96 | 2026-04-23 | ||
| DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash-0423 | DeepSeek |
1M | $0.138 | $0.275 | 2026-04-23 | ||
| DeepSeek OCR 2deepseek/deepseek-ocr-2 | DeepSeek |
8.192K | $0.03 | $0.03 | 2026-01-27 | ||
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
128K | $0.209 | $0.31 | 2025-12-01 | ||
| DeepSeek Chatdeepseek/deepseek-chat | DeepSeek |
1M | $0.15 | $0.6 | 2025-12-01 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
1M | $0.242 | $0.726 | 2025-12-01 | ||
| DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek |
163.84K | $0.19 | $0.79 | 2025-08-21 | ||
| DeepSeek-V3.1deepseek/deepseek-v3.1 | DeepSeek |
131.072K | $0.19 | $0.71 | 2025-08-21 | ||
| DeepSeek R1 0528 Qwen3 8Bdeepseek/deepseek-r1-0528-qwen3-8b | DeepSeek |
131.072K | $0.06 | $0.09 | 2025-05-29 | ||
| DeepSeek R1 0528deepseek/deepseek-r1-0528 | DeepSeek |
163.84K | $0.2 | $0.8 | 2025-05-28 | ||
| DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek |
163.84K | $0.2 | $0.8 | 2025-03-24 | ||
| DeepSeek V3 0324deepseek/deepseek-v3-0324 | DeepSeek |
163.84K | $0.28 | $1.14 | 2025-03-24 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
128K | $0.58 | $2.319 | 2025-01-20 | ||
| DeepSeek-R1-Distill-Qwen-32Bdeepseek/deepseek-r1-distill-qwen-32b | DeepSeek |
131.072K | — | — | 2025-01-20 | ||
| DeepSeek-V3deepseek/deepseek-v3 | DeepSeek |
131.072K | $0.27 | $1.1 | 2024-12-26 | ||
| DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek |
163.84K | $0.27 | $0.41 | — | ||
| DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek |
163.84K | $0.27 | $1 | — | ||
| DeepSeek: R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70b | DeepSeek |
8.192K | $0.8 | $0.8 | — | ||
| deepseek-ai/DeepSeek-V4-Prodeepseek-ai/DeepSeek-V4-Pro | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V4-Flashdeepseek-ai/DeepSeek-V4-Flash | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-OCR-2deepseek-ai/DeepSeek-OCR-2 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.2-Specialedeepseek-ai/DeepSeek-V3.2-Speciale | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.2deepseek-ai/DeepSeek-V3.2 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-Math-V2deepseek-ai/DeepSeek-Math-V2 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.2-Expdeepseek-ai/DeepSeek-V3.2-Exp | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-OCRdeepseek-ai/DeepSeek-OCR | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.2-Exp-Basedeepseek-ai/DeepSeek-V3.2-Exp-Base | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.1-Terminusdeepseek-ai/DeepSeek-V3.1-Terminus | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3.1-Basedeepseek-ai/DeepSeek-V3.1-Base | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-0528-Qwen3-8Bdeepseek-ai/DeepSeek-R1-0528-Qwen3-8B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-0528deepseek-ai/DeepSeek-R1-0528 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-Prover-V2-671Bdeepseek-ai/DeepSeek-Prover-V2-671B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Zerodeepseek-ai/DeepSeek-R1-Zero | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1deepseek-ai/DeepSeek-R1 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3-0324deepseek-ai/DeepSeek-V3-0324 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-V3deepseek-ai/DeepSeek-V3 | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-7B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Distill-Llama-8Bdeepseek-ai/DeepSeek-R1-Distill-Llama-8B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-32B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/DeepSeek-R1-Distill-Llama-70Bdeepseek-ai/DeepSeek-R1-Distill-Llama-70B | DeepSeek |
Not documented | — | — | — | ||
| deepseek-ai/Janus-Pro-1Bdeepseek-ai/Janus-Pro-1B | DeepSeek |
Not documented | — | — | — |