Llama 3.3 70B Instruct API pricing
Of the 6 providers checked, Novita AI lists the lowest blended rate for Llama 3.3 70B Instruct: $0.135 input and $0.40 output per 1M tokens, on its pricing page as of 25 September 2026.
Meta's text-only 70B model from December 2024, with a 128K context. It is older than the rest of this list but still widely hosted, which makes it a useful yardstick for what providers charge. Meta's Llama 3.3 Community License comes with its own use policy.
- Creator
- Meta
- Released
- 6 December 2024
- Weights
- Open
- License
- Llama 3.3 Community License
- Size
- 70B total
- Context
- 128K tokens
- Input
- text
- Model card
- Hugging Face
Facts from the model card, checked 25 Sep 2026.
Across 6 providers, the most expensive charges 5.2ร the cheapest on a blended basis.
Prices by provider
Per 1M tokens, on-demand, sorted cheapest first by blended cost (3:1 input to output). Off-peak and long-context rates are listed on each provider's page.
| # | Provider | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|---|
| 1 | Novita AI | $0.135 | โ | $0.40 | 25 Sep 2026 | |
| 2 | DeepInfra | $0.23 | โ | $0.40 | 25 Sep 2026 | The Turbo variant is $0.10 / $0.32 |
| 3 | IONOS AI Model Hub | โฌ0.65 โ $0.7389 | โ | โฌ0.65 โ $0.7389 | 25 Sep 2026 | Price on ionos.de; the US site lists $0.71 / $0.71 |
| 4 | Cloudflare Workers AI | $0.293 | โ | $2.253 | 25 Sep 2026 | @cf/meta/llama-3.3-70b-instruct-fp8-fast |
| 5 | Scaleway | โฌ0.90 โ $1.023 | โ | โฌ0.90 โ $1.023 | 25 Sep 2026 | |
| 6 | Together AI | $1.04 | โ | $1.04 | 25 Sep 2026 |
Each price was read off the provider's own pricing page on the date shown; the date links to that page. Providers that publish no per-token price for this model are not listed. EUR prices are ranked at the ECB reference rate of 24 September 2026. The same data is open under CC-BY at /api/query/prices.
Compare every inference provider on free tiers, hosting and EU availability in the inference APIs table.
Is your product missing?