DeepSeek V3.2
friendli/deepseek-ai/DeepSeek-V3.2 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.75
Blended $/1M (3:1)
$0.5
Input $/1M
$1.5
Output $/1M
$2.00
1M in + 1M out
$0.25 −50%
Cache read $/1M
#3567 of 7,713
Cheapest rank
- Provider
- Friendli (
friendli) - Kind
- text (outputs text)
- Context
- 163,840 tokens
- Max output
- 64,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V3.2” is offered by 25 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan | free | free | $0.00 | 131k |
| Alibaba Token Plan (China) | free | free | $0.00 | 131k |
| CrofAI | $0.18 | $0.35 | $0.22 | 164k |
| TokenGo | $0.2174 | $0.326 | $0.24 | 128k |
| Meganova | $0.26 | $0.38 | $0.29 | 164k |
| DevPass (LLM Gateway) | $0.26 | $0.38 | $0.29 | 164k |
| NovitaAI | $0.269 | $0.4 | $0.30 | 164k |
| Kilo Gateway | $0.269 | $0.4 | $0.30 | 164k |
| OpenRouter | $0.269 | $0.4 | $0.30 | 164k |
| Abacus | $0.27 | $0.4 | $0.30 | 128k |
| Helicone | $0.27 | $0.41 | $0.30 | 164k |
| NanoGPT | $0.28 | $0.42 | $0.32 | 163k |
| Friendli (this) | $0.5 | $1.5 | $0.75 | 164k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Friendli 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):