DeepSeek-V3.2
huggingface/deepseek-ai/DeepSeek-V3.2 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.31
Blended $/1M (3:1)
$0.28
Input $/1M
$0.4
Output $/1M
$0.68
1M in + 1M out
—
Cache read $/1M
#2270 of 7,710
Cheapest rank
- Provider
- Hugging Face (
huggingface) - Kind
- text (outputs text)
- Context
- 163,840 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek-V3.2” is offered by 7 providers — cheapest-effective first. Deep Infra is the cheapest at $0.29 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Deep Infra | $0.26 | $0.38 | $0.29 | 164k |
| Poe | $0.27 | $0.4 | $0.30 | 128k |
| Hugging Face (this) | $0.28 | $0.4 | $0.31 | 164k |
| Vivgrid | $0.28 | $0.42 | $0.32 | 128k |
| 302.AI | $0.29 | $0.43 | $0.32 | 128k |
| Azure | $0.58 | $1.68 | $0.85 | 128k |
| Azure Cognitive Services | $0.58 | $1.68 | $0.85 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Hugging Face 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-V3.2","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):