DeepSeek V4 Pro 0813
runinfra/deepseek-ai/DeepSeek-V4-Pro-0813 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.92
Blended $/1M (3:1)
$0.6
Input $/1M
$1.9
Output $/1M
$2.50
1M in + 1M out
$0.03 −95%
Cache read $/1M
#3577 of 6,950
Cheapest rank
- Provider
- RunInfra (
runinfra) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Pro 0813” is offered by 26 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| OrcaRouter | $0.442 | $0.884 | $0.55 | 1M |
| Eden AI | $0.5808 | $1.74 | $0.87 | 1M |
| RunInfra (this) | $0.6 | $1.9 | $0.92 | 1M |
| Merge Gateway | $0.66 | $1.98 | $0.99 | 1M |
| Vercel AI Gateway | $0.66 | $1.98 | $0.99 | 1M |
| NanoGPT | $1.1 | $2.5 | $1.45 | 1M |
| Deep Infra | $1.3 | $2.6 | $1.63 | 1M |
| Cloudflare Workers AI | $1.32 | $3.96 | $1.98 | 1M |
| Hugging Face | $1.32 | $3.96 | $1.98 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at RunInfra and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-ai/DeepSeek-V4-Pro-0813","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):