Deepseek Prover V2 671B

novita-ai/deepseek/deepseek-prover-v2-671b · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: text.

$1.15Blended $/1M (3:1)

$0.7Input $/1M

$2.5Output $/1M

$3.201M in + 1M out

—Cache read $/1M

#3365 of 5,000Cheapest rank

Provider: NovitaAI (novita-ai)
Context: 160,000 tokens
Max output: 160,000 tokens
Capabilities: text

Same model, other providers

“Deepseek Prover V2 671B” is offered by 2 providers — cheapest-effective first. This one (NovitaAI) is the cheapest.

Provider	Input	Output	Blended	Context
NovitaAI (this)	$0.7	$2.5	$1.15	160k
NanoGPT	$1	$2.5	$1.38	160k

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-prover-v2-671b","messages":[{"role":"user","content":"hello"}]}'

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