# Deepseek (latest)

> Always resolves to the newest live Deepseek model — currently DeepSeek V4 Pro (deepseek/deepseek-v4-pro). DeepSeek V4 Pro is a high-capability reasoning model from DeepSeek with a
1M-token context window on Workers AI, plus BYOK routes for other hosts.


**ID**: `deepseek/deepseek-latest`  
**Creator**: DeepSeek  
**Category**: text  
**Context**: 1M tokens  
**Family alias**: always resolves to the newest live family member — currently [`deepseek/deepseek-v4-pro`](https://anyrouter.dev/model/deepseek/deepseek-v4-pro). Specs below are deepseek/deepseek-v4-pro's.  
**Fallback order**: `deepseek/deepseek-v4-pro` → `deepseek/deepseek-v3.1` → `deepseek/deepseek-v3`  
**Pricing**: $0.21 / $0.42 per 1M · billed by your provider (BYOK)  
**Released**: 2026-05-01  
**Web page**: https://anyrouter.dev/model/deepseek/deepseek-latest

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, reasoning, streaming, coding, function-calling

**Aliases**: `deepseek-v4-pro`, `deepseek-ai/deepseek-v4-pro-0813`

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-latest",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| deepseek-byok | $1.32/M (list) | $3.96/M (list) |
| baseten-byok | $0.55/M (list) | $2.19/M (list) |
| opencode-zen-byok | $0.55/M (list) | $2.19/M (list) |
| opencode-go-byok | $0.55/M (list) | $2.19/M (list) |
| commandcode-byok | $0.55/M (list) | $2.19/M (list) |
| router-byok | $1.74/M (list) | $3.48/M (list) |
| vercel-byok | $1.32/M (list) | $3.96/M (list) |
| openrouter-byok | $0.21/M (list) | $0.42/M (list) |
| deepinfra-byok | $1.30/M (list) | $2.60/M (list) |
| novita-byok | $1.60/M (list) | $3.20/M (list) |
| siliconflow-byok | $0.55/M (list) | $2.19/M (list) |
| gmicloud-byok | $1.74/M (list) | $3.48/M (list) |
| huggingface-byok | $0.55/M (list) | $2.19/M (list) |
| venice-byok | $1.65/M (list) | $3.30/M (list) |
| onetoken-byok | $0.02/M (list) | $0.05/M (list) |
| nousresearch-byok | $0.94/M (list) | $1.89/M (list) |
| beatapi-byok | $0.33/M (list) | $0.99/M (list) |
| tokenharbor-byok | $1.32/M (list) | $3.96/M (list) |
| computrix-byok | $1.74/M (list) | $3.48/M (list) |
| inference-net-byok | $1.32/M (list) | $3.96/M (list) |
| inference-net-byok | $2.10/M (list) | $4.20/M (list) |
| zenmux-byok | $0.66/M (list) | $1.98/M (list) |
| requesty-byok | $1.32/M (list) | $3.96/M (list) |
| llmgateway-byok | $0.66/M (list) | $1.98/M (list) |
| phala-byok | $1.45/M (list) | $4.36/M (list) |
| getvibe-byok | $0.19/M (list) | $0.56/M (list) |
| itera-byok | $0.60/M (list) | $1.79/M (list) |
| aihubmix-byok | $0.55/M (list) | $2.19/M (list) |
| ollama-byok | $0.55/M (list) | $2.19/M (list) |
| orcarouter-byok | $0.55/M (list) | $2.19/M (list) |
| opengateway-byok | $1.19/M (list) | $3.56/M (list) |
| wafer-byok | $0.55/M (list) | $2.19/M (list) |
| chutes-byok | $0.55/M (list) | $2.19/M (list) |
| edenai-byok | $0.55/M (list) | $2.19/M (list) |
| ofox-byok | $0.55/M (list) | $2.19/M (list) |
| abacus-byok | $0.55/M (list) | $2.19/M (list) |
| hilinkup-byok | $1.32/M (list) | $3.96/M (list) |
| fluence-byok | $1.44/M (list) | $2.89/M (list) |
| cortecs-byok | $0.55/M (list) | $2.19/M (list) |
| poe-byok | $0.55/M (list) | $2.19/M (list) |
| empiriolabs-byok | $0.55/M (list) | $2.19/M (list) |
| kenari-byok | $0.55/M (list) | $2.19/M (list) |

BYOK routes are billed by your own provider key — AnyRouter charges $0. Rates marked (list) are the provider's published list price.

## Benchmarks

- **GPQA Diamond**: 0.7
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.9
- **SciCode**: 0.4
- **OTIS Mock AIME**: 1.0
- **SimpleQA (verified)**: 0.6

Benchmark data from [Epoch AI](https://epoch.ai/benchmarks) (CC-BY 4.0).