DeepSeek V3.2 Thinking
vercel/deepseek/deepseek-v3.2-thinking · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.93
Blended $/1M (3:1)
$0.62
Input $/1M
$1.85
Output $/1M
$2.47
1M in + 1M out
—
Cache read $/1M
#3947 of 7,708
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V3.2 Thinking” is offered by 2 providers — cheapest-effective first. NanoGPT is the cheapest at $0.32 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.28 | $0.42 | $0.32 | 163k |
| Vercel AI Gateway (this) | $0.62 | $1.85 | $0.93 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vercel AI Gateway 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-thinking","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):