jishie

Deepseek V3.1 Terminus

novita-ai/deepseek/deepseek-v3.1-terminus · family deepseek · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.45Blended $/1M (3:1)
$0.27Input $/1M
$1Output $/1M
$1.271M in + 1M out
$0.135 −50%Cache read $/1M
#2102 of 5,000Cheapest rank
Provider
NovitaAI (novita-ai)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“Deepseek V3.1 Terminus” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.36 blended.

ProviderInputOutputBlendedContext
NanoGPT$0.25$0.7$0.36128k
NovitaAI (this)$0.27$1$0.45131k
Helicone$0.27$1$0.45128k
Abacus$0.27$1$0.45128k
Vercel AI Gateway$0.27$1$0.45131k
OpenRouter$0.27$1$0.45164k

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-v3.1-terminus","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):