jishie

Llama 3.2 3B Instruct

nvidia/meta/llama-3.2-3b-instruct · family llama · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#316 of 7,710
Cheapest rank
Provider
Nvidia (nvidia)
Kind
text (outputs text)
Context
32,768 tokens
Max output
32,000 tokens
Capabilities
text

Same model, other providers

“Llama 3.2 3B Instruct” is offered by 8 providers — cheapest-effective first. This one (Nvidia) is the cheapest.

ProviderInputOutputBlendedContext
Nvidia (this)freefree$0.0033k
Inference$0.02$0.02$0.0216k
NovitaAI$0.03$0.05$0.0433k
DevPass (LLM Gateway)$0.03$0.05$0.0433k
NanoGPT$0.0306$0.0493$0.04131k
OpenRouter$0.05$0.33$0.12131k
Cloudflare Workers AI$0.0509$0.335$0.1280k
Pioneer$0.1$0.335$0.16131k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Nvidia and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"meta/llama-3.2-3b-instruct","messages":[{"role":"user","content":"hello"}]}'

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

← all Nvidia models · model index · JSON