gmicloud/deepseek-ai/DeepSeek-V4-Flash · family deepseek-flash · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.
gmicloud)“DeepSeek V4 Flash” is offered by 9 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 1000k |
| UnoRouter | free | free | $0.00 | 1000k |
| Alibaba Token Plan | free | free | $0.00 | 1000k |
| Umans AI Coding Plan | free | free | $0.00 | 1049k |
| Alibaba Token Plan (China) | free | free | $0.00 | 1000k |
| UnoRouter | $0.0625 | $0.125 | $0.08 | 1000k |
| NanoGPT | $0.07 | $0.14 | $0.09 | 1049k |
| DigitalOcean | $0.0679 | $0.168 | $0.09 | 1049k |
| GMI Cloud (this) | $0.112 | $0.224 | $0.14 | 1049k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at GMI Cloud 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-Flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):