Llama-3.3-70B-Instruct
As of Nov 18, 2026, the cheapest Llama-3.3-70B-Instruct API price is $0.05 per 1M input tokens (NanoGPT) and $0.23 per 1M output tokens (NanoGPT). Llama-3.3-70B-Instruct is offered by 29 providers in the llama family, open weights. One provider lists it as a free-tier offer.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| NanoGPTopenmeta-llama/llama-3.3-70b-instruct | Cheapest$0.05 | Cheapest$0.23 | $0.025 | — | 131k | — |
| Obscurify.aiopenmeta-llama/llama-3.3-70b-instruct | $0.0553 | $0.2541 | — | — | 128k | — |
| Meganovaopenmeta-llama/Llama-3.3-70B-Instruct | $0.1 | $0.3 | — | — | 131k | — |
| Eden AIopendeepinfra/meta-llama/Llama-3.3-70B-Instruct | $0.1 | $0.32 | — | — | 131k | — |
| Kilo Gatewayopenmeta-llama/llama-3.3-70b-instruct | $0.1 | $0.32 | — | — | 128k | — |
| Heliconeopenllama-3.3-70b-instruct | $0.13 | $0.39 | — | — | 128k | — |
| DevPass (LLM Gateway)openllama-3.3-70b-instruct | $0.135 | $0.4 | — | — | 131k | — |
| LLM Gatewayopennovita/llama-3.3-70b-instruct | $0.135 | $0.4 | — | — | 131k | — |
| Novita AIopenmeta-llama/llama-3.3-70b-instruct | $0.135 | $0.4 | — | — | 12k | — |
| Inference APIsopenmeta-llama/Llama-3.3-70B-Instruct-Turbo | $0.2 | $0.5 | — | — | 131k | — |
| Merge Gatewayopenmeta/llama-3.3-70b-instruct | $0.22 | $0.5 | $0.11 | — | 131k | — |
| Hugging Faceopenmeta-llama/Llama-3.3-70B-Instruct | $0.59 | $0.79 | — | — | 131k | — |
| IO.NETopenmeta-llama/Llama-3.3-70B-Instruct | $0.5466 | $1.0226 | $0.2733 | — | 128k | 27d agoout +169.1% |
| Azureopenllama-3.3-70b-instruct | $0.71 | $0.71 | — | — | 128k | — |
| Azure Cognitive Servicesopenllama-3.3-70b-instruct | $0.71 | $0.71 | — | — | 128k | — |
| OpenRouteropenmeta-llama/llama-3.3-70b-instruct | $0.71 | $0.71 | $0.71 | — | 131k | 8d agoout −10.1% |
| Vercel AI Gatewayopenmeta/llama-3.3-70b | $0.72 | $0.72 | — | — | 128k | 27d ago |
| Cortecsopenllama-3.3-70b-instruct | $0.724 | $0.724 | — | — | 131k | 62d ago |
| Neonopenmeta-llama-3-3-70b-instruct | $0.5 | $1.5 | — | — | 128k | — |
| watsonx.aiopenmeta-llama/llama-3-3-70b-instruct | $0.7526 | $0.7526 | — | — | 131k | — |
| Eden AIopenscaleway/llama-3.3-70b-instruct | $0.9913 | $0.9913 | — | — | 128k | todayout −0.3% |
| Scalewayopenllama-3.3-70b-instruct | $1.0093 | $1.0093 | — | — | 100k | 27d agoout +12.1% |
| evrocopennvidia/Llama-3.3-70B-Instruct-FP8 | $1.15 | $1.15 | — | — | 128k | — |
| Eden AIopengreenpt/llama-3.3-70b-instruct | $1.2115 | $1.2115 | — | — | 128k | todayout −0.3% |
| GreenPTopenllama-3.3-70b-instruct | $1.254 | $1.254 | — | — | 100k | — |
| Prime Inferenceopenmeta-llama/llama-3.3-70b-instruct | $1.04 | $2.253 | — | — | 131k | — |
| Phalaopenmeta-llama/llama-3.3-70b-instruct | $2 | $2 | — | — | 131k | — |
| Tinfoilopenllama3-3-70b | $1.75 | $2.75 | — | — | 131k | — |
| CloudFerro Sherlockopenmeta-llama/Llama-3.3-70B-Instruct | $2.92 | $2.92 | — | — | 70k | — |
| Pendrafreellama3.3:70b | free | free | — | — | 128k | — |
Llama-3.3-70B-Instruct price history
Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 7 providers whose rate moved. Each step is a recorded change. All recent price changes.
| Date | Provider | 1M input | 1M output | Change |
|---|---|---|---|---|
| Eden AI | $0.9947 → $0.9913 | $0.9947 → $0.9913 | −0.3% | |
| Eden AI | $1.2157 → $1.2115 | $1.2157 → $1.2115 | −0.3% | |
| Eden AI | $1.2189 → $1.2157 | $1.2189 → $1.2157 | −0.3% | |
| Eden AI | $0.9973 → $0.9947 | $0.9973 → $0.9947 | −0.3% | |
| Eden AI | $1.224 → $1.2189 | $1.224 → $1.2189 | −0.4% | |
| Eden AI | $1.0014 → $0.9973 | $1.0014 → $0.9973 | −0.4% | |
| Eden AI | $1.0093 → $1.0014 | $1.0093 → $1.0014 | −0.8% | |
| Eden AI | $1.2335 → $1.224 | $1.2335 → $1.224 | −0.8% | |
| Eden AI | $1.0074 → $1.0093 | $1.0074 → $1.0093 | +0.2% | |
| Eden AI | $1.2312 → $1.2335 | $1.2312 → $1.2335 | +0.2% | |
| OpenRouter | $0.59 → $0.71 | $0.79 → $0.71 | −10.1% | |
| Eden AI | $1.2282 → $1.2312 | $1.2282 → $1.2312 | +0.3% | |
| Eden AI | $1.0049 → $1.0074 | $1.0049 → $1.0074 | +0.3% | |
| Eden AI | $1.0102 → $1.0049 | $1.0102 → $1.0049 | −0.5% | |
| Eden AI | $1.2346 → $1.2282 | $1.2346 → $1.2282 | −0.5% | |
| OpenRouter | $0.2 → $0.59 | $0.52 → $0.79 | +51.9% | |
| Eden AI | $1.2394 → $1.2346 | $1.2394 → $1.2346 | −0.4% | |
| Eden AI | $1.014 → $1.0102 | $1.014 → $1.0102 | −0.4% | |
| Eden AI | $1.0061 → $1.014 | $1.0061 → $1.014 | +0.8% | |
| Eden AI | $1.2297 → $1.2394 | $1.2297 → $1.2394 | +0.8% |
Llama-3.3-70B-Instruct pricing FAQ
What is the cheapest Llama-3.3-70B-Instruct API?
As of Nov 18, 2026, NanoGPT has the lowest Llama-3.3-70B-Instruct output price at $0.23 per 1M tokens, and NanoGPT has the lowest input price at $0.05 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Llama-3.3-70B-Instruct?
29 providers list Llama-3.3-70B-Instruct on Sovyron; 29 of them sell it at a metered per-token price.
Is Llama-3.3-70B-Instruct free?
One provider lists a free-tier offer: Pendra. Free tiers usually have rate limits.
What is the context window of Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct supports a 131k-token context window and up to 131k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—