jishie

Llama-3.3-70B-Instruct

pendra/llama3.3:70b · family llama · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
Cache read $/1M
#266 of 6,825
Cheapest rank
Provider
Pendra (pendra)
Kind
text (outputs text)
Context
128,000 tokens
Max output
4,096 tokens
Capabilities
tools text

Same model, other providers

“Llama-3.3-70B-Instruct” is offered by 23 providers — cheapest-effective first. This one (Pendra) is the cheapest.

ProviderInputOutputBlendedContext
Pendra (this)freefree$0.00128k
Llamafreefree$0.00128k
Vercel AI Gatewayfreefree$0.00128k
OpenRouter$0.1$0.32$0.16131k
Eden AI$0.1$0.32$0.16131k
Kilo Gateway$0.1$0.32$0.16131k
Cortecs$0.129$0.399$0.20131k
Nebius Token Factory$0.13$0.4$0.20128k
DevPass (LLM Gateway)$0.13$0.4$0.20131k
Crusoe$0.25$0.75$0.38128k
Charm Hyper$0.598$0.738$0.63128k
Hugging Face$0.59$0.79$0.64131k
Abacus$0.59$0.79$0.64131k

Call it

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

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"llama3.3:70b","messages":[{"role":"user","content":"hello"}]}'

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

← all Pendra models · model index · JSON