DeepSeek-V3
qiniu-ai/deepseek-v3 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.51
Blended $/1M (3:1)
$0.2899
Input $/1M
$1.16
Output $/1M
$1.45
1M in + 1M out
—
Cache read $/1M
#3096 of 8,512
Cheapest rank
- Provider
- Qiniu (
qiniu-ai) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 16,000 tokens
- Capabilities
- tools text
Same model, other providers
“DeepSeek-V3” is offered by 5 providers — cheapest-effective first. Deep Infra is the cheapest at $0.46 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.32 | $0.89 | $0.46 | 164k |
| Qiniu (this) | $0.2899 | $1.16 | $0.51 | 128k |
| Hugging Face | $0.4 | $1.3 | $0.63 | 64k |
| Novita AI | $0.89 | $0.89 | $0.89 | 64k |
| Together AI | $1.25 | $1.25 | $1.25 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Qiniu and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-v3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):