# DeepSeek: deepseek-v4-pro-260425

- Model ID: `deepseek-v4-pro-260425`
- Provider: DeepSeek
- Web version: https://www.moleapi.com/en/models/deepseek/deepseek-v4-pro
- Content status: alias

## Model introduction

DeepSeek V4-Pro is the Pro model in DeepSeek's V4 family. DeepSeek's update notes confirm access through both OpenAI Chat Completions and Anthropic interfaces.

## Model capabilities

- OpenAI compatible
- Prompt cache
- Reasoning

### Verified specifications

- Official model parameter: deepseek-v4-pro
- Verified interfaces: OpenAI Chat Completions; Anthropic
- Official announcement date: 2026-04-24

## Model pricing and access

Pricing is supplied dynamically by the MoleAPI console API.

### Standard (default, x1)

| Tier | Condition | Input | Output | Cache read |
| --- | --- | ---: | ---: | ---: |
| peak | - | $1.32 | $4 | $0.044 |
| off_peak | - | $0.66 | $2 | $0.022 |

### Access protocols

| Protocol | Method | Endpoint |
| --- | --- | --- |
| openai | POST | /v1/chat/completions |

- Live pricing source: https://home.moleapi.com/api/pricing

## About deepseek-v4-pro-260425

DeepSeek V4-Pro is the Pro model in DeepSeek's V4 family. DeepSeek's update notes confirm access through both OpenAI Chat Completions and Anthropic interfaces.

### Best for

Low-cost long-context reasoning, coding agents, or open-weight deployments that also need OpenAI- and Anthropic-compatible interfaces.

### Core strengths

- A 1M context window, up to 384K output, and both thinking and non-thinking modes.
- An open-weight MoE model with 1.6T total and 49B active parameters.
- Strong independent results in its open-weight cohort with low first-token latency and price.

### Limitations

- Official API material confirms text input only; multimodal support should not be inferred from the name.
- Reasoning mode changes quality, speed, and token use, so comparisons must pin the effort profile.

### Selection and production evaluation

Start a deepseek-v4-pro-260425 evaluation by mapping its official positioning to real work: Low-cost long-context reasoning, coding agents, or open-weight deployments that also need OpenAI- and Anthropic-compatible interfaces. The first pass should exercise both its main strength, "A 1M context window, up to 384K output, and both thinking and non-thinking modes.", and its known limitation, "Official API material confirms text input only; multimodal support should not be inferred from the name.", instead of relying on a single subjective general-chat comparison.

For access, MoleAPI currently lists openai protocols and the Standard billing groups for this DeepSeek model; the default price summary is Input $1.32 / 1M tokens · Output $4 / 1M tokens. Pricing, protocols, and groups come from the live catalog, so production planning should still price representative requests using real context length, output size, and cache-hit assumptions.

No independent ranking is shown unless it matches this exact model ID and reasoning profile, so nearby variants are not used as a proxy. Before launch, pin the model ID, prompt, and sample set, then compare task accuracy, structured-output validity, tool-call success, and timeout rates under the same conditions.

The model material on this page was last checked on 2026-07-23. When upstream model cards, context limits, or tool support change, update the cited bilingual facts before changing the recommendation; live MoleAPI price changes remain separate and update from the catalog automatically.

### Sources

- [DeepSeek models and pricing documentation](https://api-docs.deepseek.com/quick_start/pricing/) — DeepSeek
- Last verified: 2026-07-23

## Code examples

### cURL

```bash
curl https://api.moleapi.com/v1/chat/completions \
  -H "Authorization: Bearer $MOLEAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-pro-260425","messages":[{"role":"user","content":"Hello"}]}'
```

## More related models

- [deepseek-v4.1-flash](https://www.moleapi.com/en/models/deepseek/deepseek-v4.1-flash) — DeepSeek
- [deepseek-v4-flash](https://www.moleapi.com/en/models/deepseek/deepseek-v4-flash) — DeepSeek
- [deepseek-v4-flash-vision-exp](https://www.moleapi.com/en/models/deepseek/deepseek-v4-flash-vision-exp) — DeepSeek
- [gpt-5.4-nano](https://www.moleapi.com/en/models/openai/gpt-5.4-nano) — OpenAI
- [gpt-5.6-luna](https://www.moleapi.com/en/models/openai/gpt-5.6-luna) — OpenAI
- [gpt-5-mini](https://www.moleapi.com/en/models/openai/gpt-5-mini) — OpenAI

## Frequently asked questions

### How is deepseek-v4-pro-260425 priced?

Prices are read from the MoleAPI console API and update with model prices, context tiers, and account groups.

### How can I access deepseek-v4-pro-260425?

The catalog currently lists openai.

### How do I switch an existing project to deepseek-v4-pro-260425?

Keep the MoleAPI API address and key, replace the model parameter, and check protocol-specific parameters.

### Where do the deepseek-v4-pro-260425 details come from?

Capabilities and limitations are checked against DeepSeek and the other cited pages; pricing and protocols come from the MoleAPI console.