Llama 3.3 70B Instruct API pricing
As of October 21, 2026, Meta Llama 3.3 70B Instruct costs $0.10 per million input tokens and $0.32 per million output tokens through OpenRouter.
Llama 3.3 70B Instruct benchmarks and specs · Every Meta Llama model's price
- Input, per million tokens$0.10
- Output, per million tokens$0.32
- Cached input, per millionNo cache price listed
- Context window131K tokens
- Max output16K tokens
- Output speed97 tok/s
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0003 | $0.260 | Yes |
| Repository review | 50K input + 3K output tokens | $0.0060 | $5.96 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.023 | $23.20 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We have recorded 1 price change since we started reading the price daily on October 15, 2026.
- October 15, 2026 First recorded: $0.59 input, $0.79 output
- October 17, 2026 $0.79 to $0.32 output, $0.59 to $0.10 input
Cheaper models as good as Llama 3.3 70B Instruct
Models within two points of Llama 3.3 70B Instruct or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Ling 3.0 Flash$0.063 Overall 20.1 against 7.7 · 80% cheaper output
- Llama 3.1 8B Instruct$0.08 Overall 6.9 against 7.7 · 75% cheaper output
- Mistral Small 3$0.08 Overall 6.7 against 7.7 · 75% cheaper output
- gpt-oss-20b$0.09 Overall 10.0 against 7.7 · 72% cheaper output
- Qwen3.5-9B$0.13 Overall 13.3 against 7.7 · 59% cheaper output
Llama 3.3 70B Instruct pricing questions
- How much does Llama 3.3 70B Instruct cost per million tokens?
- $0.10 per million input tokens and $0.32 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does Llama 3.3 70B Instruct support prompt caching?
- OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.
- Is there a cheaper model as good as Llama 3.3 70B Instruct?
- Ling 3.0 Flash scores 20.1 on the Artificial Analysis Intelligence Index, within two points of Llama 3.3 70B Instruct or above it, and costs $0.063 per million output tokens.
- Has the price of Llama 3.3 70B Instruct changed?
- Yes, 1 time since October 15, 2026; the dates are listed on this page.