# DeepSeek models

Canonical HTML page: [DeepSeek models](<https://impossibl.com/deepseek>)
Markdown alternative: [DeepSeek models as Markdown](<https://impossibl.com/deepseek.md>)

Access 7 models from DeepSeek through the Impossibl API, including DeepSeek V3.2, DeepSeek V3.2 Speciale, and DeepSeek V4 Flash. Compare API pricing, context windows, and capabilities.

Select two or three models to [compare specifications and API costs](<https://impossibl.com/compare.md>). Model types and billing units are not interchangeable.

## Models

### [DeepSeek V3.2](<https://impossibl.com/deepseek/deepseek-v3-2>)

DeepSeek V3.2 is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 163,840 tokens. The advertised input rate is $0.58 per million input tokens. The advertised output rate is $1.68 per million output tokens.

- API identifier: `deepseek/deepseek-v3-2`
- Creator: DeepSeek; model type: Text generation.
- Context window: 163,840 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v3-2.md>)

### [DeepSeek V3.2 Speciale](<https://impossibl.com/deepseek/deepseek-v3-2-speciale>)

DeepSeek V3.2 Speciale is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 163,840 tokens. The advertised input rate is $0.58 per million input tokens. The advertised output rate is $1.68 per million output tokens.

- API identifier: `deepseek/deepseek-v3-2-speciale`
- Creator: DeepSeek; model type: Text generation.
- Context window: 163,840 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.58 per million input tokens; $1.68 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v3-2-speciale.md>)

### [DeepSeek V4 Flash](<https://impossibl.com/deepseek/deepseek-v4-flash>)

DeepSeek V4 Flash is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $0.19 per million input tokens. The advertised output rate is $0.51 per million output tokens.

- API identifier: `deepseek/deepseek-v4-flash`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.19 per million input tokens; $0.51 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-flash.md>)

### [DeepSeek V4 Flash 0731](<https://impossibl.com/deepseek/deepseek-v4-flash-0731>)

DeepSeek V4 Flash 0731 is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $0.14 per million input tokens. The advertised output rate is $0.28 per million output tokens.

- API identifier: `deepseek/deepseek-v4-flash-0731`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $0.14 per million input tokens; $0.28 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-flash-0731.md>)

### [DeepSeek V4 Pro](<https://impossibl.com/deepseek/deepseek-v4-pro>)

DeepSeek V4 Pro is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,000,000 tokens. The advertised input rate is $1.74 per million input tokens. The advertised output rate is $3.48 per million output tokens.

- API identifier: `deepseek/deepseek-v4-pro`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,000,000 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.74 per million input tokens; $3.48 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-pro.md>)

### [DeepSeek V4 Pro 0813](<https://impossibl.com/deepseek/deepseek-v4-pro-0813>)

DeepSeek V4 Pro 0813 is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $1.74 per million input tokens. The advertised output rate is $3.48 per million output tokens.

- API identifier: `deepseek/deepseek-v4-pro-0813`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text; outputs: text.
- Base API pricing (USD): $1.74 per million input tokens; $3.48 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4-pro-0813.md>)

### [DeepSeek V4.1 Flash](<https://impossibl.com/deepseek/deepseek-v4.1-flash>)

DeepSeek V4.1 Flash is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 1,048,576 tokens. The advertised input rate is $0.30 per million input tokens. The advertised output rate is $1.20 per million output tokens.

- API identifier: `deepseek/deepseek-v4.1-flash`
- Creator: DeepSeek; model type: Text generation.
- Context window: 1,048,576 tokens; tool calling: Not published.
- Inputs: text, image; outputs: text.
- Base API pricing (USD): $0.30 per million input tokens; $1.20 per million output tokens.
- [Complete model facts, cache rates, context tiers, and FAQs as Markdown](<https://impossibl.com/deepseek/deepseek-v4.1-flash.md>)

## Compare DeepSeek models

- [DeepSeek V3.2 vs DeepSeek V3.2 Speciale](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v3-2-speciale>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v3-2-speciale.md>)
- [DeepSeek V3.2 vs DeepSeek V4 Flash](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-flash>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-flash.md>)
- [DeepSeek V3.2 vs DeepSeek V4 Flash 0731](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-flash-0731>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-flash-0731.md>)
- [DeepSeek V3.2 vs DeepSeek V4 Pro](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-pro>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-pro.md>)
- [DeepSeek V3.2 vs DeepSeek V4 Pro 0813](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-pro-0813>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4-pro-0813.md>)
- [DeepSeek V3.2 vs DeepSeek V4.1 Flash](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4.1-flash>); [Markdown comparison](<https://impossibl.com/compare/deepseek/deepseek-v3-2/deepseek/deepseek-v4.1-flash.md>)

## Frequently asked questions

### Which DeepSeek models are available through Impossibl?

The directory lists 7 models from DeepSeek available through the Impossibl API, including DeepSeek V3.2, DeepSeek V3.2 Speciale, and DeepSeek V4 Flash. Open each model page for its API identifier, capabilities, and current pricing.

### How much do DeepSeek models cost?

DeepSeek model prices vary by model and usage. All rates below are published base API rates in USD. For token-priced models, published input rates start at $0.14 per million input tokens. Published output rates start at $0.28 per million output tokens. Input and output minima may refer to different models. Individual model pages include published cache prices and billing units. Applicable fees and workspace-specific pricing can affect the amount paid.

### What context windows do DeepSeek models support?

Among DeepSeek models with a published limit on Impossibl, the largest context window is 1,048,576 tokens, listed for DeepSeek V4 Flash 0731, DeepSeek V4 Pro 0813, and DeepSeek V4.1 Flash. Context limits vary by model and are separate from maximum output limits.

### What inputs and capabilities do DeepSeek models support?

Available model types include text generation. Published input support includes image and text; support varies by model. Tool-calling support is unspecified for 7 models.

### How do I use DeepSeek models through an API?

Use the exact model identifier from the model page with the Impossibl API. For example, select deepseek/deepseek-v3-2 with /v1/chat/completions. Endpoint compatibility depends on the selected model. The API quickstart explains how to create an API key and send a request.

## Sources and related links

Prices, capabilities, limits, and availability describe the public Impossibl API offering. An unpublished fact is unknown; a published zero price is zero. Compare matching billing units and check context tiers before estimating costs.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Model directory as Markdown](<https://impossibl.com/models.md>)
- [API quickstart](<https://impossibl.com/docs/agent-quickstart>)
- [Model documentation](<https://impossibl.com/docs/models>)