Llama 3.3 70B Instruct API price
On OpenCheap, Llama 3.3 70B Instruct (Meta) costs $0.022 per 1M input tokens and $0.070 per 1M output tokens (cached input $0.0039), through one OpenAI-compatible API.
Prices updated 2026-11-03 09:09 UTC.
Price per 1M tokens
| Input, our price | $0.022 |
|---|---|
| Output, our price | $0.070 |
| Cached input, our price | $0.0039 |
| Context length | 131K tokens |
| OpenRouter list, input · output | $0.200 · $0.520 |
| vs list | −87% |
“vs list” compares our price with OpenRouter's list price on a 1:3 input:output blend, as on the Models page.
How to call Llama 3.3 70B Instruct
Base URL https://api.opencheap.si/v1, model id opencheap/llama-3.3-70b, and an API key from the console. Any OpenAI SDK works.
curl https://api.opencheap.si/v1/chat/completions \
-H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "opencheap/llama-3.3-70b", "messages": [{ "role": "user", "content": "Hi" }] }'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.opencheap.si/v1", api_key=os.environ["OPENCHEAP_API_KEY"])
r = client.chat.completions.create(model="opencheap/llama-3.3-70b",
messages=[{"role": "user", "content": "Hi"}])
print(r.choices[0].message.content)FAQ
What is the cheapest Llama 3.3 70B Instruct API?
On OpenCheap, Llama 3.3 70B Instruct costs $0.022 per 1M input tokens and $0.070 per 1M output tokens, and cached input $0.0039 per 1M tokens. Each request is routed to the cheapest healthy source for the model. You pay from one prepaid balance, with no monthly fee.
Is it OpenAI-compatible?
Yes. Point any OpenAI SDK or HTTP client at the base URL https://api.opencheap.si/v1 with an OpenCheap API key, and call /chat/completions with the model id opencheap/llama-3.3-70b. Requests and responses have the same shape as OpenAI's chat completions, streaming included.
Does it work with Cursor, Claude Code or Codex?
Yes. In Cursor, add the custom model opencheap/llama-3.3-70b with the base URL https://api.opencheap.si/v1. In Claude Code, set ANTHROPIC_BASE_URL to https://api.opencheap.si and ANTHROPIC_MODEL to opencheap/llama-3.3-70b. In Codex, add OpenCheap as a model provider with base_url https://api.opencheap.si/v1. The quickstart has each setup step by step.
More Meta models
- Llama 4 Maverick$0.200 · $0.300
- Llama 4 Scout$0.110 · $0.320
- Llama 3.05 Storybreaker Ministral 70b$0.740 · $0.740
- Llama 3.1 70B Instruct$0.420 · $0.420
- meta-llama/Llama-3.1-8B-Instruct$0.030 · $0.060
- Llama 3.2 1B Instruct$0.029 · $0.220
- Llama 3.2 3B$0.046 · $0.130
- Llama 3.3 70B Instruct abliterated$1.10 · $1.10