Llama 3.3 70B Instruct
io-net/meta-llama/Llama-3.3-70B-Instruct · family llama · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.67
Blended $/1M (3:1)
$0.5466
Input $/1M
$1.02
Output $/1M
$1.57
1M in + 1M out
$0.2733 −50%
Cache read $/1M
#3631 of 8,512
Cheapest rank
- Provider
- IO.NET (
io-net) - 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 9 providers — cheapest-effective first. NanoGPT is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.05 | $0.23 | $0.10 | 131k |
| Meganova | $0.1 | $0.3 | $0.15 | 131k |
| Merge Gateway | $0.22 | $0.5 | $0.29 | 131k |
| IO.NET (this) | $0.5466 | $1.02 | $0.67 | 128k |
| Vertex | $0.72 | $0.72 | $0.72 | 128k |
| Amazon Bedrock | $0.72 | $0.72 | $0.72 | 128k |
| Regolo AI | $0.6 | $2.7 | $1.13 | 128k |
| Prime Inference | $1.04 | $2.25 | $1.34 | 131k |
| CloudFerro Sherlock | $2.92 | $2.92 | $2.92 | 70k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at IO.NET 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/Llama-3.3-70B-Instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):