DeepSeek V3.1 Terminus
vercel/deepseek/deepseek-v3.1-terminus · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.45
Blended $/1M (3:1)
$0.27
Input $/1M
$1
Output $/1M
$1.27
1M in + 1M out
$0.135 −50%
Cache read $/1M
#2682 of 7,712
Cheapest rank
- Provider
- Vercel AI Gateway (
vercel) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V3.1 Terminus” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.36 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.25 | $0.7 | $0.36 | 128k |
| Vercel AI Gateway (this) | $0.27 | $1 | $0.45 | 131k |
| NovitaAI | $0.27 | $1 | $0.45 | 131k |
| Abacus | $0.27 | $1 | $0.45 | 128k |
| OpenRouter | $0.27 | $1 | $0.45 | 164k |
| Helicone | $0.27 | $1 | $0.45 | 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-v3.1-terminus","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):