# DeepSeek Chat

> DeepSeek V3-generation non-thinking chat model, served by third-party hosts.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `deepseek/deepseek-chat`
- Status: available
- Released: —
- Context: 128K tokens
- Max output: 16K tokens
- Input: text; output: text
- Knowledge cutoff: 2024-07

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.682 | per 1M tokens |
| Output | $2.035 | per 1M tokens |
| Cache read | $0.0682 | per 1M tokens |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:deepseek/deepseek-chat`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Amazon Bedrock | `bedrock:deepseek/deepseek-chat` | United States | $0.682 | $2.035 | no |

## Endpoints

| API | Request | model |
| --- | --- | --- |
| OpenAI Chat | POST https://api.ohmygpt.com/v1/chat/completions | `deepseek/deepseek-chat` |
| OpenAI Responses | POST https://api.ohmygpt.com/v1/responses | `deepseek/deepseek-chat` |
| Anthropic Messages | POST https://api.ohmygpt.com/v1/messages | `deepseek/deepseek-chat` |
| Google Gemini | POST https://api.ohmygpt.com/v1/models/deepseek/deepseek-chat:generateContent | `deepseek/deepseek-chat` |

## Example

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

Web page: https://www.ohmygpt.com/models/deepseek/deepseek-chat