DeepSeek · Official-source model record
DeepSeek-V4-Pro-0813
DeepSeek · Version DeepSeek-V4-Pro-0813
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about DeepSeek-V4-Pro-0813
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
Which DeepSeek-V4-Pro-0813 does this page describe?
DeepSeek-V4-Pro-0813 is a model record from DeepSeek in the DeepSeek family. Source
The recorded model identifier or checkpoint is DeepSeek-V4-Pro-0813. Use that exact identifier when checking documentation or a provider listing. Source
How can you access DeepSeek-V4-Pro-0813?
The catalog documents API and Open weights access for DeepSeek-V4-Pro-0813. Source 1 · Source 2
As of the catalog check, this version was listed as available. Source
For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.
How much does DeepSeek-V4-Pro-0813 cost?
The recorded token rates for DeepSeek-V4-Pro-0813 are:
- Input: US$1.32 per 1 million input tokens. Source
- Output: US$3.96 per 1 million output tokens. Source
Rate conditions: Published standard USD per million tokens, uncached input; region, prompt length, caching and service-tier adjustments may apply. See official source. Source 1 · Source 2
Illustrative arithmetic: 10,000 input tokens plus 2,000 output tokens would cost US$0.02112 at those recorded rates. This assumes every token is billed at the displayed rate and excludes any cache, batch, tool, storage or tier adjustments; it is not a quote or measured usage.
Check the source's pricing conditions before budgeting. A token rate does not state the price of an app subscription or the full cost of running downloaded weights.
What are DeepSeek-V4-Pro-0813's context and output limits?
The documented context window is 1,000,000 tokens. Source
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What can DeepSeek-V4-Pro-0813 receive and generate?
Documented inputs: text. Source
Documented outputs: text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for DeepSeek-V4-Pro-0813?
The recorded license label is mit. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What is documented about the DeepSeek-V4-Pro-0813 checkpoint?
This evidence refers to deepseek-ai/DeepSeek-V4-Pro-0813 at recorded revision 72e1d3230f6c080a530b0a1d46f8eb4602340597, checked October 23, 2026. Repository metadata
Safetensors metadata records 1,650,497,936,906 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: DeepseekV4ForCausalLM. Repository metadata
Repository task tag: text-generation. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata
Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
What the configuration file says
The pinned config.json contains these values. Pinned configuration
max_position_embeddings- 1,048,576
rope_scaling- {"beta_fast":32,"beta_slow":1,"factor":16,"original_max_position_embeddings":65536,"type":"yarn"}
sliding_window- 128
torch_dtype- bfloat16
num_attention_heads- 128
num_key_value_heads- 1
num_hidden_layers- 61
hidden_size- 7,168
Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other DeepSeek models from DeepSeek.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
deepseek-coder-1.3b-base
Open weights
deepseek-coder-1.3b-instruct
Open weights
deepseek-coder-33b-base
Open weights
deepseek-coder-33b-instruct
Open weights
deepseek-coder-5.7bmqa-base
Open weights
deepseek-coder-6.7b-base
Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- DeepSeekSource ↗
- Family
- DeepSeekSource ↗
- Version
- DeepSeek-V4-Pro-0813Source ↗
- Availability
- AvailableSource ↗
- Access
- API · Open weightsSource 1 ↗Source 2 ↗
- Inputs
- TextSource ↗
- Outputs
- TextSource ↗
- Context window
- 1,000,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Not documented
- License
- mitSource ↗
- Input price / 1M tokens
- $1.32Source ↗
- Output price / 1M tokens
- $3.96Source ↗
Read this with the numbers.
Official publisher weight listing; availability refers to this distribution, not a guaranteed hosted API. Base, SFT and research variants are identified by their exact published names. API documentation reports a 1M context and 384K maximum output; exact integer output ceiling is not independently specified, so maxOutputTokens is null. Prices shown are standard peak-period uncached rates; off-peak rates are lower. The current hosted API routes the stable deepseek-v4-pro identifier to this version. That stable string is kept on its separate official weight identity rather than duplicated as an alias here. Publisher repository evidence (2026-10-23): Publisher task label: text-generation. Published architecture metadata: DeepseekV4ForCausalLM. Repository library label: transformers. Published safetensors metadata counts 1,650,497,936,906 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published configuration: max_position_embeddings=1048576; sliding_window=128; dtype=bfloat16; 61 hidden layers. The configuration includes explicit RoPE scaling ({"beta_fast":32,"beta_slow":1,"factor":16,"original_max_position_embeddings":65536,"type":"yarn"}); no effective context extension is inferred. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Published standard USD per million tokens, uncached input; region, prompt length, caching and service-tier adjustments may apply. See official source.
Model identifiers and aliases 2
DeepSeek-V4-Pro-0813deepseek-ai/DeepSeek-V4-Pro-0813
Follow the evidence
Official sources.
- Official DeepSeek model documentation ↗api-docs.deepseek.com
- DeepSeek-V4-Pro-0813 official model card ↗huggingface.co
- DeepSeek-V4-Pro-0813: official publisher repository metadata ↗huggingface.co
- DeepSeek-V4-Pro-0813: publisher model card at revision 72e1d3230f6c ↗huggingface.co
- DeepSeek-V4-Pro-0813: published checkpoint configuration at revision 72e1d3230f6c ↗huggingface.co