ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
109 models
DeepSeek
DeepSeek: DeepSeek V4.1 Flash T
Reasoning Tools JSON Open weights

DeepSeek V4.1 Flash model for reasoning and agentic coding

deepseek/deepseek-v4.1-flash 2026-09-10 1M context $0.15/M input $0.6/M output
23 providers
DeepSeek: DeepSeek V4 Flash Vision Exp T
Reasoning Tools JSON

Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work

deepseek/deepseek-v4-flash-vision-exp 2026-08-21 1M context $0.15/M input $0.6/M output
19 providers
DeepSeek: DeepSeek V4 Pro 0813 T
Reasoning Tools JSON Open weights

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

deepseek/deepseek-v4-pro-0813 2026-08-12 1M context $0.442/M input $0.884/M output
30 providers
DeepSeek: DeepSeek V4 Flash 0731 T
Reasoning Tools JSON Open weights

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

deepseek/deepseek-v4-flash-0731 2026-07-31 1M context $0.035/M input $0.07/M output
43 providers
DeepSeek: DeepSeek V4 Flash T
Reasoning Tools JSON Open weights

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

deepseek/deepseek-v4-flash 2026-04-24 1M context $0.15/M input $0.6/M output
62 providers
DeepSeek: DeepSeek V4 Pro T
Reasoning Tools JSON Open weights

Open MoE flagship with million-token context for coding and long agent runs

deepseek/deepseek-v4-pro 2026-04-24 1M context $0.435/M input $0.87/M output
62 providers
DeepSeek: DeepSeek V4 Flash 0423 T
Reasoning Open weights

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

deepseek/deepseek-v4-flash-0423 2026-04-23 1M context $0.139/M input $0.278/M output
2 providers
DeepSeek: DeepSeek V4 Pro 0423 T
Reasoning Tools JSON Open weights

DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes

deepseek/deepseek-v4-pro-0423 2026-04-23 1M context $1.32/M input $3.96/M output
2 providers
DeepSeek: DeepSeek OCR 2 T
Open weights

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

deepseek/deepseek-ocr-2 2026-01-27 8.192K context $0.03/M input $0.03/M output
3 providers
DeepSeek: DeepSeek V3.2 T
Reasoning Tools JSON Open weights

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

deepseek/deepseek-v3.2 2025-12-01 128K context $0.18/M input $0.35/M output
24 providers
DeepSeek: DeepSeek Reasoner T
Open weights

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

deepseek/deepseek-reasoner 2025-12-01 1M context $0.147/M input $0.295/M output
6 providers
DeepSeek: DeepSeek Chat T
Tools Open weights

DeepSeek chat model for instruction following, coding, and analysis

deepseek/deepseek-chat 2025-12-01 1M context $0.147/M input $0.295/M output
8 providers
DeepSeek: DeepSeek-V3.1 T
Reasoning Tools Open weights

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

deepseek/deepseek-v3.1 2025-08-21 131.072K context $0.19/M input $0.71/M output
10 providers
DeepSeek: DeepSeek V3 0324 T
Tools JSON Open weights

March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding

deepseek/deepseek-v3-0324 2025-03-24 163.84K context $0.2/M input $0.8/M output
9 providers
DeepSeek: DeepSeek-R1-Distill-Qwen-32B T
Open weights

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

deepseek/deepseek-r1-distill-qwen-32b 2025-01-20 131.072K context $0.3/M input $0.3/M output
1 provider
DeepSeek: DeepSeek-R1 T
Reasoning Tools Open weights

Classic open reasoning model for transparent math, coding, and deliberate problem solving

deepseek/deepseek-r1 2025-01-20 128K context $0.7/M input $2.5/M output
14 providers
DeepSeek: DeepSeek-V3 T
Tools Open weights

Open DeepSeek MoE chat model for coding, math, and general reasoning

deepseek/deepseek-v3 2024-12-26 131.072K context $0.27/M input $1.12/M output
8 providers
DeepSeek: deepseek-ai/DeepSeek-OCR
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-OCR Not documented context Input not listed Output not listed
DeepSeek: deepseek-ai/DeepSeek-V3.2-Exp
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-V3.2-Exp Not documented context Input not listed Output not listed
DeepSeek: deepseek-ai/DeepSeek-Math-V2
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-Math-V2 Not documented context Input not listed Output not listed
DeepSeek: DeepSeek: DeepSeek V3.2 Exp T

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/deepseek-v3.2-exp 163.84K context $0.27/M input $0.41/M output
DeepSeek: deepseek-ai/DeepSeek-V4-Flash
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-V4-Flash Not documented context Input not listed Output not listed
DeepSeek: DeepSeek: DeepSeek V4 Flash Vision Exp (batch) T

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...

deepseek/deepseek-v4-flash-vision-exp:batch 1.04858M context $0.11/M input $0.33/M output
DeepSeek: DeepSeek: DeepSeek V3 0324 T

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

deepseek/deepseek-chat-v3-0324 163.84K context $0.25/M input $1/M output
DeepSeek: DeepSeek: R1 0528 T

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

deepseek/deepseek-r1-0528 163.84K context $0.5/M input $2.15/M output
DeepSeek: DeepSeek: DeepSeek V4 Pro 0813 (batch) T

DeepSeek 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-0813:batch 1.04858M context $0.66/M input $1.98/M output
DeepSeek: DeepSeek: R1 Distill Llama 70B T

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...

deepseek/deepseek-r1-distill-llama-70b 8.192K context $0.8/M input $0.8/M output
DeepSeek: deepseek-ai/DeepSeek-V4-Pro
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-V4-Pro Not documented context Input not listed Output not listed
DeepSeek: DeepSeek: DeepSeek V3.1 T

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

deepseek/deepseek-chat-v3.1 163.84K context $0.25/M input $0.95/M output
DeepSeek: deepseek-ai/DeepSeek-OCR-2
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-OCR-2 Not documented context Input not listed Output not listed
DeepSeek: deepseek-ai/DeepSeek-V3.2
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-V3.2 Not documented context Input not listed Output not listed
DeepSeek: deepseek-ai/DeepSeek-V4.1-Flash
Open weights

No provider description is available for this model yet.

deepseek-ai/DeepSeek-V4.1-Flash Not documented context Input not listed Output not listed
DeepSeek: DeepSeek: DeepSeek V3.1 Terminus T

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/deepseek-v3.1-terminus 131.072K context $0.27/M input $1/M output