Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
 DeepInfraturbo, fp8 | $0.4 | $0.4 | $0.4 / $0.4Cheapest | n/a | Cheapest |
 AWS BedrockDefault region | $0.72 | $0.72 | $0.72 / $0.72+80% vs cheapest | n/a | +80% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $48.00 direct.
Helicone$48.00+0%
Kong AI Gateway$48.00+0%
LiteLLM$48.00+0%
Vercel AI Gateway$48.00+0%
Cloudflare AI Gateway$50.40+5%
Requesty$50.40+5%
Eden AI$50.64+5.5%
OpenRouter$50.64+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
| Muse Spark 1.3 Contributor Meta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
| Muse Spark 1.2 Contributor Meta · 1M | $0.1 | $0.2 | $0.1 / $0.2 | $0.125 | 1M | Lab list price | · |
| Muse Glimmer 30B Meta · 131K | $0.3 | $1.1 | $0.3 / $1.1 | $0.5 | 131K | on Phala | · |
 GLM 5.3Z.ai · 1.31M | $0.561 | $1.76 | $0.561 / $1.76 | $0.862 | 1.31M | on Baidu (fp8) | · |
| GLM 4.6 Z.ai · 205K | $0.43 | $1.75 | $0.43 / $1.75 | $0.76 | 205K | on Venice (fp4) | · |
 DeepSeek V4.1 FlashDeepSeek · 1MCheapest: $0.131 on Morph | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.131 on Morph | · |
 Gemini 3.1 Flash LiteGoogle · 1MCheapest: $0.281 on Google Vertex AI (global-flex) | $0.25 | $1.5 | $0.25 / $1.5 | $0.563 | 1M | $0.281 on Google Vertex AI (global-flex) | · |
About Llama 3.1 70B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors.
Takes text in and returns text. First listed Sep 23, 2026. Up to 16K output tokens. Blended price $0.4 per 1M tokens at 3 input to 1 output. Model id llama-3-1-70b-instruct.
Price history
No list-price history: this model is sold by hosts rather than its lab.
Questions
How much does Llama 3.1 70B Instruct cost?
$0.4 per million input tokens and $0.4 per million output tokens.
What is the context window of Llama 3.1 70B Instruct?
131K tokens, with up to 16K tokens of output.
Where is Llama 3.1 70B Instruct cheapest?
Of 2 routes tracked, DeepInfra is cheapest at $0.4 input and $0.4 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.