Llama-3.3-70B-Instruct

snowflake-cortex/snowflake-llama3.3-70b · family llama · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

—Blended $/1M (3:1)

—Input $/1M

—Output $/1M

—1M in + 1M out

—Cache read $/1M

—Cheapest rank

Provider: Snowflake Cortex (snowflake-cortex)
Context: 128,000 tokens
Max output: 4,096 tokens
Capabilities: toolstext

Same model, other providers

“Llama-3.3-70B-Instruct” is offered by 9 providers — cheapest-effective first. Llama is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Llama	free	free	$0.00	128k
Vercel AI Gateway	free	free	$0.00	128k
Kilo Gateway	$0.1	$0.32	$0.16	131k
OpenRouter	$0.1	$0.32	$0.16	131k
Cortecs	$0.129	$0.399	$0.20	131k
Nebius Token Factory	$0.13	$0.4	$0.20	128k
LLM Gateway	$0.13	$0.4	$0.20	131k
Charm Hyper	$0.598	$0.738	$0.63	128k
Snowflake Cortex (this)	—	—	—	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Snowflake Cortex and pass this model id:

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

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