Overall · Snapshot captured:
- Artificial Analysis Intelligence Index
- 30.4
- Coding Index
- 59.4
- Agentic Index
- 26.3
Near-frontier quality at ~1/6 the cost of Opus 4.7 / GPT-5.5
Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick - Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
| Provider | Input /1M | Output /1M | Cache read /M | Latency | Throughput | Uptime | Context |
|---|---|---|---|---|---|---|---|
BytePlus | $1.32 (cheapest) | $3.96 (cheapest) | $0.044 | - | - | - | 1M |
Cloudflare | $1.32 (cheapest) | $3.96 (cheapest) | $0.044 | - | - | - | 1M |
Alibaba Cloud | $2.40 | $4.80 | $0.20 | - | - | - | 1M |
Rates from the DOS.AI catalog for the billing units shown. Caching and provider discounts mean the price actually paid is often below the listed one.
Provider↕ | Effective in /M↕ | Effective out /M↕ | Cache read /M↕ | Latency↕ | Throughput↕ | Uptime↕ | Savings↕ |
|---|---|---|---|---|---|---|---|
BytePlus | $1.32$1.23 | $3.96 | $0.04 | - | - | - | -7% |
Cloudflare | $1.32$0.55 | $3.96 | $0.04 | - | - | - | -58% |
Alibaba Cloud | $2.40$1.08 | $4.80 | $0.20 | - | - | - | -55% |
Success rate across observed provider requests. This is historical sample data, not live health or an uptime guarantee.
Not enough observations
Last 7 days
There are not enough valid request observations to report a success rate.
Dated third-party measurements with source links.
Overall · Snapshot captured:
Overall · Snapshot captured:
Use the DOS API to integrate DeepSeek V4 Pro into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'