Llama 3.3 70B: Pricing, Context, and Benchmarks

Llama 3.3 70B is Meta's Llama 3 model released on 2024-12-06. It runs on a 128K-token context window, priced at $0.59/M input and $0.79/M output. Open-weight 70B model. Near-405B quality at a fraction of the cost. Together AI list price below.

Specifications

Benchmark scores

Scores reflect single measurements on the date shown. Reproducibility varies; consult the linked source for methodology. Use the comparison tool for side-by-side analysis.

What this model is good for

Based on benchmark scores and capability fit, Llama 3.3 70B ranks well for:

• High-Throughput Inference — rank #1. Groq serves this at ~500 tokens/sec — fastest in class.
• Best Open-Weight Model — rank #3. Most permissive license + widest tooling support. The "standard" open default.

Cost calculator

For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0014 per call. For typical usage:

For more precise estimates including caching discounts, use the LLM API Cost Calculator.

Other Meta models

• Llama 3.1 405B

Common comparisons

• Llama 3.3 70B vs DeepSeek-R1 Side-by-side specs, pricing, and benchmarks
• Llama 3.3 70B vs Qwen3-235B Side-by-side specs, pricing, and benchmarks
• Llama 3.3 70B vs Gemini 2.5 Flash Side-by-side specs, pricing, and benchmarks
• Llama 3.3 70B vs DeepSeek-V3 Side-by-side specs, pricing, and benchmarks

API setup

curl https://api.together.xyz/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "llama-3-3-70b", "messages": [{"role": "user", "content": "Hello"}]}'

See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.