jishie

Llama 3.3 70B

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

$2.00
Blended $/1M (3:1)
$1.75
Input $/1M
$2.75
Output $/1M
$4.50
1M in + 1M out
$1.75
Cache read $/1M
#5248 of 7,708
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
128,000 tokens
Max output
16,384 tokens
Capabilities
text

Same model, other providers

“Llama 3.3 70B” is offered by 6 providers — cheapest-effective first. STACKIT is the cheapest at $0.59 blended.

ProviderInputOutputBlendedContext
STACKIT$0.53$0.76$0.59128k
Groq$0.59$0.79$0.64131k
CoreWeave$0.71$0.71$0.71128k
Together AI$1.04$1.04$1.04131k
Venice AI$0.7$2.8$1.22128k
NanoGPT (this)$1.75$2.75$2.00128k

Call it

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

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

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

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

← all NanoGPT models · model index · JSON