Llama 3.3 70B Instruct API pricing
Of the 10 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.
Across 10 providers, the most expensive charges 7.9Γ 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 | $0.135 | β | $0.40 | 25 Sep 2026 | ||
| 2 | $0.23 | β | $0.40 | 25 Sep 2026 | The Turbo variant is $0.10 / $0.32 | |
| 3 | β¬0.60 β $0.682 | β | β¬0.65 β $0.7389 | 1 Oct 2026 | ||
| 4 | β¬0.65 β $0.7389 | β | β¬0.65 β $0.7389 | 25 Sep 2026 | Price on ionos.de; the US site lists $0.71 / $0.71 | |
| 5 | $0.293 | β | $2.253 | 25 Sep 2026 | @cf/meta/llama-3.3-70b-instruct-fp8-fast | |
| 6 | β¬0.60 β $0.682 | β | β¬1.20 β $1.364 | 15 Oct 2026 | Excl. VAT. Same on cloud.infercom.ai/plans/pricing. | |
| 7 | β¬0.90 β $1.023 | β | β¬0.90 β $1.023 | 25 Sep 2026 | ||
| 8 | $1.04 | β | $1.04 | 25 Sep 2026 | ||
| 9 | β¬1.04 β $1.1822 | β | β¬1.04 β $1.1822 | 1 Oct 2026 | ||
| 10 | β¬1.39 β $1.58 | β | β¬1.39 β $1.58 | 1 Oct 2026 | Listed in SimpleCredits (100 SC = EUR 1); homepage advertises 20% off during the open beta |
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.
Of the 6 European-headquartered providers checked, Melious AI lists the lowest blended rate for Llama 3.3 70B Instruct: β¬0.60 input and β¬0.65 output per 1M tokens, on its pricing page as of 1 October 2026.
European providers
Per 1M tokens, on-demand, for providers headquartered in Europe, sorted cheapest first by blended cost (3:1 input to output). See all European AI providers
| # | Provider | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|---|
| 1 | β¬0.60 β $0.682 | β | β¬0.65 β $0.7389 | 1 Oct 2026 | ||
| 2 | β¬0.65 β $0.7389 | β | β¬0.65 β $0.7389 | 25 Sep 2026 | Price on ionos.de; the US site lists $0.71 / $0.71 | |
| 3 | β¬0.60 β $0.682 | β | β¬1.20 β $1.364 | 15 Oct 2026 | Excl. VAT. Same on cloud.infercom.ai/plans/pricing. | |
| 4 | β¬0.90 β $1.023 | β | β¬0.90 β $1.023 | 25 Sep 2026 | ||
| 5 | β¬1.04 β $1.1822 | β | β¬1.04 β $1.1822 | 1 Oct 2026 | ||
| 6 | β¬1.39 β $1.58 | β | β¬1.39 β $1.58 | 1 Oct 2026 | Listed in SimpleCredits (100 SC = EUR 1); homepage advertises 20% off during the open beta |
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.
Want these prices in your AI assistant? Try the Infrabase MCP server
Compare every inference provider on free tiers, hosting and EU availability in the inference APIs table.
Is your product missing?