DeepSeek V3.2
abacus/deepseek-ai/DeepSeek-V3.2 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.30
Blended $/1M (3:1)
$0.27
Input $/1M
$0.4
Output $/1M
$0.67
1M in + 1M out
—
Cache read $/1M
#2398 of 8,512
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V3.2” is offered by 21 providers — cheapest-effective first. Alibaba Token Plan (China) is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan (China) | free | free | $0.00 | 131k |
| Alibaba Token Plan | free | free | $0.00 | 131k |
| NanoGPT | $0.2088 | $0.3096 | $0.23 | 163k |
| TokenGo | $0.2174 | $0.326 | $0.24 | 128k |
| Kilo Gateway | $0.26 | $0.38 | $0.29 | 164k |
| Meganova | $0.26 | $0.38 | $0.29 | 164k |
| OpenRouter | $0.26 | $0.38 | $0.29 | 164k |
| DevPass (LLM Gateway) | $0.26 | $0.38 | $0.29 | 164k |
| Abacus (this) | $0.27 | $0.4 | $0.30 | 128k |
| Helicone | $0.27 | $0.41 | $0.30 | 164k |
| Merge Gateway | $0.28 | $0.4 | $0.31 | 128k |
| Ofox | $0.29 | $0.43 | $0.32 | 128k |
| ZenMux | $0.293 | $0.4395 | $0.33 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus 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):