DeepSeek V4 Pro 0813
hyper/deepseek-v4-pro-0813 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$2.16
Blended $/1M (3:1)
$1.44
Input $/1M
$4.31
Output $/1M
$5.75
1M in + 1M out
$0.0479 −97%
Cache read $/1M
#5881 of 8,511
Cheapest rank
- Provider
- Charm Hyper (
hyper) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V4 Pro 0813” is offered by 38 providers — cheapest-effective first. Alibaba Token Plan (China) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| Alibaba Token Plan | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| RunInfra | $0.6 | $1.9 | $0.92 | 1M |
| NanoGPT | $0.6587 | $1.98 | $0.99 | 1M |
| Vercel AI Gateway | $0.66 | $1.98 | $0.99 | 1M |
| Ollama Cloud | $0.66 | $1.98 | $0.99 | 1M |
| OrcaRouter | $0.66 | $1.98 | $0.99 | 1M |
| AIHubMix | $0.6918 | $2.08 | $1.04 | 1M |
| IteraCompute | $0.79 | $2.38 | $1.19 | 1M |
| OpenRouter | $0.111 | $4.44 | $1.19 | 1M |
| Boundless | $1.04 | $2.08 | $1.30 | 1M |
| Charm Hyper (this) | $1.44 | $4.31 | $2.16 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Charm Hyper and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro-0813","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):