Llama 3.3 70B API Pricing / Price per 1M tokens
Meta • API Price Comparison
Also known as: meta-llama-3-3-70b-instruct · meta llama 3 3 70b instruct · metallama3370binstruct · meta-llama3-3-70b-instruct · meta llama3 3 70b instruct · llama-3.3-70b · llama3.370b · llama3.3-70b · llama3.3 70b
Updated on · Published currencies / per 1M tokens; cheapest ranked by input
| Channel | Input / 1M | Output / 1M | Cache read / 1M | Updated / verified on |
|---|---|---|---|---|
| Official | No official quote recorded | |||
| OpenRouterLowest input | USD 0.59 | USD 0.79 | USD 0.295 | 2026-10-15 |
— means the price or date is not recorded. Cross-currency ranking uses exchange rates.
Llama 3.3 70B is a large language model by Meta with a 131K-token context window. Across the 1 API channels tracked here, input pricing ranges from $0.59 per 1M input tokens; the cheapest is OpenRouter at $0.59 per 1M input tokens. None of the tracked channels are directly reachable from mainland China without a proxy or VPN. Prices are collected daily from official provider pages and every tracked channel, then cross-checked by a data-accuracy audit.
| Channel | Type | Input / 1M | Output / 1M | Rate Limit | China | vs Official | |
|---|---|---|---|---|---|---|---|
OpenRouter12 variants💰 Best Price | 聚合平台 | $0.59 | $0.79 | - | - | - | |
Show all price variants for this channelOpenRouter Auto / default routeDefault $0.59 / $0.79 per 1M default_route Cheapest endpoint: DeepInfra $0.10 / $0.32 per 1M cheapest_endpoint DeepInfra | meta-llama/llama-3.3-70b-instruct $0.10 / $0.32 per 1M upstream_provider Novita | meta-llama/llama-3.3-70b-instruct $0.14 / $0.40 per 1M upstream_provider AkashML | meta-llama/llama-3.3-70b-instruct $0.20 / $0.52 per 1M upstream_provider Parasail | meta-llama/llama-3.3-70b-instruct $0.22 / $0.50 per 1M upstream_provider Cloudflare | meta-llama/llama-3.3-70b-instruct $0.29 / $2.25 per 1M upstream_provider SambaNova | meta-llama/llama-3.3-70b-instruct $0.45 / $0.90 per 1M upstream_provider Groq | meta-llama/llama-3.3-70b-instruct $0.59 / $0.79 per 1M upstream_provider CoreWeave | meta-llama/llama-3.3-70b-instruct $0.71 / $0.71 per 1M upstream_provider Google | meta-llama/llama-3.3-70b-instruct $0.72 / $0.72 per 1M upstream_provider Google | meta-llama/llama-3.3-70b-instruct $0.72 / $0.72 per 1M upstream_provider | |||||||
| Usage Level | Tokens/Month | OpenRouter |
|---|---|---|
| 🐣 Light | 0.1M in + 0.1M out | $0.10 |
| 📊 Medium | 1.0M in + 0.5M out | $0.99 |
| 🚀 Heavy | 10.0M in + 5.0M out | $9.85 |
| 🏢 Enterprise | 100.0M in + 50.0M out | $98.50 |
Frequently asked questions about llama-3.3-70b
How much does the Llama 3.3 70B API cost?
The lowest input rate is USD 0.59 per 1M tokens; output on that channel is USD 0.79 per 1M tokens.
Which channel has the cheapest Llama 3.3 70B API?
OpenRouter has the lowest input rate: USD 0.59 per 1M tokens. Cross-currency ranking uses exchange rates; compare output and cache prices separately.
What is the Llama 3.3 70B cache-read price?
OpenRouter: USD 0.295 per 1M cache-read tokens.
When was Llama 3.3 70B pricing last updated?
Updated on 2026-10-15. This is the latest recorded price update or verification; see the table for individual channel dates.