Deepseek V3.2 Exp
novita-ai/deepseek/deepseek-v3.2-exp · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.30
Blended $/1M (3:1)
$0.27
Input $/1M
$0.41
Output $/1M
$0.68
1M in + 1M out
—
Cache read $/1M
#2241 of 7,710
Cheapest rank
- Provider
- NovitaAI (
novita-ai) - Kind
- text (outputs text)
- Context
- 163,840 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Deepseek V3.2 Exp” is offered by 5 providers — cheapest-effective first. Meganova is the cheapest at $0.30 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Meganova | $0.27 | $0.4 | $0.30 | 164k |
| NovitaAI (this) | $0.27 | $0.41 | $0.30 | 164k |
| OpenRouter | $0.27 | $0.41 | $0.30 | 164k |
| NanoGPT | $0.28 | $0.42 | $0.32 | 164k |
| Alibaba (China) | $0.287 | $0.431 | $0.32 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NovitaAI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v3.2-exp","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):