novita-ai/meta-llama/llama-3.2-3b-instruct · family llama · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: text.
novita-ai)“Llama 3.2 3B Instruct” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 33k |
| Inference | $0.02 | $0.02 | $0.02 | 16k |
| NovitaAI (this) | $0.03 | $0.05 | $0.04 | 33k |
| LLM Gateway | $0.03 | $0.05 | $0.04 | 33k |
| NanoGPT | $0.0306 | $0.0493 | $0.04 | 131k |
| OpenRouter | $0.05 | $0.33 | $0.12 | 131k |
| Cloudflare Workers AI | $0.0509 | $0.335 | $0.12 | 80k |
| Cloudflare AI Gateway | $0.051 | $0.34 | $0.12 | 128k |
| Pioneer | $0.1 | $0.335 | $0.16 | 131k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at NovitaAI 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-3.2-3b-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):