---
title: "Llama 3.3 70B API pricing: 14 providers compared | BroadRouter"
description: "Llama 3.3 70B API price per token from 14 providers: lowest listed USD 0.10 input and USD 0.32 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/llama-3.3-70b-instruct/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Llama 3.3 70B API pricing

Updated 2026-11-15

Among the 14 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Llama 3.3 70B is DeepInfra at USD 0.10 per 1M input tokens and USD 0.32 per 1M output tokens. The median across 14 standard prices is USD 0.625 / USD 0.72. Meta sells no API of its own for it.

Meta · slug `llama-3.3-70b-instruct` · up to 131,072 tokens of context · 14 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-15. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/). Archived list prices since 2025-07-09 (4 archived price points, 0 list-price changes): [LLM API price history](https://broadrouter.com/data/llm-api-price-history/#p-deepinfra).

## Does Meta sell Llama 3.3 70B directly?

No. Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. [Checked 2026-11-14](https://dev.meta.ai/docs/overview).

## Llama 3.3 70B model facts

Facts from Meta's model card for [`meta-llama/Llama-3.3-70B-Instruct`](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

Llama 3.3 70B: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes, with gated access. meta-llama/Llama-3.3-70B-Instruct is public, but Hugging Face asks you to request access and accept the terms before you download (gated: manual). | [Hugging Face model API](https://huggingface.co/api/models/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “"private": false, "gated": "manual", 30 .safetensors files listed” |
| Licence | Llama 3.3 Community License Agreement (custom commercial license) | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “A custom commercial license, the Llama 3.3 Community License Agreement” |
| Total parameters | 70B | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “Llama 3.3 (text only) \| A new mix of publicly available online data. \| 70B” |
| Context length | 128k | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “Multilingual Text and code \| 128k” |
| Input and output | Multilingual text in; multilingual text and code out | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “Input modalities … Output modalities … Multilingual Text … Multilingual Text and code” |
| Tool calling | Yes | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “LLaMA-3.3 supports multiple tool use formats.” |
| Release date | 2024-12-06 | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “70B Instruct: December 6, 2024” |
| First published on Hugging Face (not necessarily the release date) | 2024-11-26 | [Hugging Face model API](https://huggingface.co/api/models/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 · Quote: “"createdAt": "2024-11-26T16:08:47.000Z"” |

## Llama 3.3 70B price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 7.9× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

Llama 3.3 70B API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** cheapest · `meta-llama/Llama-3.3-70B-Instruct-Turbo` · Note: DeepInfra Turbo variant (quantized). Quote: “$0.10 in $0.32 out / 1M tokens” | USD 0.10 | not published | USD 0.32 | USD 0.155 | 131,072 | FP8 | [DeepInfra page](https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo) · checked 2026-11-14 · re-checked 2026-11-16 |
| 2 | **[Novita AI](https://broadrouter.com/llm-api-pricing/providers/novita/)** · `meta-llama/llama-3.3-70b-instruct` · Quote: “Llama 3.3 70B Instruct 12K $0.135 /Mt $0.4 /Mt” | USD 0.135 | not published | USD 0.40 | USD 0.2013 | 12,288 | not stated | [Novita AI page](https://novita.ai/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 3 | **[AkashML](https://broadrouter.com/llm-api-pricing/providers/akashml/)** · `meta-llama/Llama-3.3-70B-Instruct` · Quote: “Price (per 1M Tokens) Input Output Cache Read Llama 3.3 70B $0.20 $0.52 $0.10” | USD 0.20 | USD 0.10 | USD 0.52 | USD 0.28 | 131,072 | not stated | [AkashML page](https://akashml.com/models/llama-3-3-70b) · checked 2026-11-15 · re-checked 2026-11-16 |
| 4 | **[Parasail](https://broadrouter.com/llm-api-pricing/providers/parasail/)** · Quote: “Llama 3.3 70B (FP8) $0.22 $0.50 $0.11” | USD 0.22 | USD 0.11 | USD 0.50 | USD 0.29 | not stated | FP8 | [Parasail page](https://www.parasail.io/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 5 | **[GMI Cloud](https://broadrouter.com/llm-api-pricing/providers/gmi-cloud/)** · `meta-llama/Llama-3.3-70B-Instruct` · Note: No cache-read price published. Quote: “Price (per 1M tokens) Input $0.25 Output $0.75” | USD 0.25 | not published | USD 0.75 | USD 0.375 | 131,072 | BF16 | [GMI Cloud page](https://console.gmicloud.ai/model/llm/llama-3-3-70b-instruct/d9755097-53db-4a09-bf63-f8150f4c39fb) · checked 2026-11-15 · re-checked 2026-11-16 |
| 6 | **[Featherless](https://broadrouter.com/llm-api-pricing/providers/featherless/)** · `meta-llama/Llama-3.3-70B-Instruct` · Note: Developer plan (per-token billing, from 50 USD a month in credits). Quote: “PRICING: INPUT $0.65 / CACHED $0.52 / OUTPUT $0.75” | USD 0.65 | USD 0.52 | USD 0.75 | USD 0.675 | 32,768 | FP8 | [Featherless page](https://featherless.ai/models/meta-llama/Llama-3.3-70B-Instruct) · checked 2026-11-15 · re-checked 2026-11-16 |
| 7 | **[CoreWeave Forge](https://broadrouter.com/llm-api-pricing/providers/coreweave/)** · `meta-llama/Llama-3.3-70B-Instruct` · Quote: “Meta Llama 3.3 70B $0.71 $0.71 -” | USD 0.71 | not published | USD 0.71 | USD 0.71 | 128,000 | not stated | [CoreWeave Forge page](https://coreweave.com/forge-pricing/inference-agents) · checked 2026-11-15 · re-checked 2026-11-16 |
| 8 | **[Microsoft Azure](https://broadrouter.com/llm-api-pricing/providers/azure/)** · Note: Foundry Models serverless (pay-as-you-go), Global deployment. Quote: “Llama 3.3 70B Global $0.71 $0.71” | USD 0.71 | not published | USD 0.71 | USD 0.71 | not stated | not stated | [Microsoft Azure page](https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/llama/) · checked 2026-11-14 · re-checked 2026-11-16 |
| 9 | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** · Note: Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Llama 3.3 Instruct (70B) $0.72 $0.72 $0.36 $0.36” | USD 0.72 | not published | USD 0.72 | USD 0.72 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| 10 | **[Google Vertex AI](https://broadrouter.com/llm-api-pricing/providers/google-vertex/)** · `llama-3.3-70b` · Quote: “Llama 3.3 70B Input $0.72 … Output $0.72” | USD 0.72 | not published | USD 0.72 | USD 0.72 | not stated | not stated | [Google Vertex AI page](https://cloud.google.com/model-garden/partner-models/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 11 | **[SambaNova](https://broadrouter.com/llm-api-pricing/providers/sambanova/)** · `Meta-Llama-3.3-70B-Instruct` · Quote: “Meta-Llama-3.3-70B-Instruct N/A 0.60 USD 1.20 USD” | USD 0.60 | not published | USD 1.20 | USD 0.75 | not stated | not stated | [SambaNova page](https://cloud.sambanova.ai/plans/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 12 | **[IBM watsonx.ai](https://broadrouter.com/llm-api-pricing/providers/ibm-watsonx/)** · `llama-3-3-70b-instruct` · Note: Single published per-1M rate; IBM bills Resource Units "equivalent to 1000 tokens (including both input and output tokens)", so input and output cost the same. Quote: “llama-3-3-70b-instruct Meta USD 0.7526” | USD 0.7526 | not published | USD 0.7526 | USD 0.7526 | not stated | not stated | [IBM watsonx.ai page](https://www.ibm.com/products/watsonx-ai/pricing) · checked 2026-11-15 · re-checked 2026-11-16 |
| 13 | **[Cloudflare Workers AI](https://broadrouter.com/llm-api-pricing/providers/cloudflare/)** · `@cf/meta/llama-3.3-70b-instruct-fp8-fast` · Note: Cloudflare publishes this USD per-token price alongside the neuron price. Quote: “@cf/meta/llama-3.3-70b-instruct-fp8-fast $0.293 per M input tokens $2.253 per M output tokens” | USD 0.293 | not published | USD 2.253 | USD 0.783 | not stated | FP8 | [Cloudflare Workers AI page](https://developers.cloudflare.com/workers-ai/platform/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| 14 | **[Venice](https://broadrouter.com/llm-api-pricing/providers/venice/)** · `llama-3.3-70b` · Quote: “\| Llama 3.3 70B \| `llama-3.3-70b` \| $0.70 \| $2.80 \| — \| — \| Private \|” | USD 0.70 | not published | USD 2.80 | USD 1.225 | 128,000 | FP8 | [Venice page](https://docs.venice.ai/pricing) · checked 2026-11-15 · re-checked 2026-11-16 |
| — | **[Amazon Bedrock](https://broadrouter.com/llm-api-pricing/providers/amazon-bedrock/)** batch · Note: Batch columns. Shown for region US East (N. Virginia) on the pricing page (values filled from AWS's published price list for us-east-1). Quote: “Llama 3.3 Instruct (70B) $0.72 $0.72 $0.36 $0.36” | USD 0.36 | not published | USD 0.36 | USD 0.36 | not stated | not stated | [Amazon Bedrock page](https://aws.amazon.com/bedrock/pricing/) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[Google Vertex AI](https://broadrouter.com/llm-api-pricing/providers/google-vertex/)** batch · `llama-3.3-70b` · Quote: “Llama 3.3 70B Batch Input $0.36 … Batch Output $0.36” | USD 0.36 | not published | USD 0.36 | USD 0.36 | not stated | not stated | [Google Vertex AI page](https://cloud.google.com/model-garden/partner-models/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** flex / spot · `meta-llama/Llama-3.3-70B-Instruct-Turbo` · Note: Flex service tier (0.8× standard). DeepInfra Turbo variant (quantized). Quote: “Flex (0.8×) $0.08 $0.256” | USD 0.08 | not published | USD 0.256 | USD 0.124 | 131,072 | FP8 | [DeepInfra page](https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Other tiers (batch and flex / spot):** batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Llama%203.3%2070B%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fllama-3.3-70b-instruct%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What does Llama 3.3 70B cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=llama-3.3-70b-instruct). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on Llama 3.3 70B, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **DeepInfra** | USD 14.76 | USD 28.80 | USD 208.80 |
| **Novita AI** | USD 19.35 | USD 38.40 | exceeds context |
| **AkashML** | USD 21.96 | USD 48.60 | USD 253.80 |
| **Parasail** | USD 22.86 | USD 52.38 | USD 272.70 |
| **GMI Cloud** | USD 36.00 | USD 71.25 | USD 517.50 |
| **Featherless** | USD 64.98 | USD 157.89 | exceeds context |
| **CoreWeave Forge** | USD 76.68 | USD 181.05 | USD 1,342 |
| **Microsoft Azure** | USD 76.68 | USD 181.05 | USD 1,342 |
| **Amazon Bedrock** | USD 77.76 | USD 183.60 | USD 1,361 |
| **Google Vertex AI** | USD 77.76 | USD 183.60 | USD 1,361 |
| **SambaNova** | USD 75.60 | USD 162.00 | USD 1,188 |
| **IBM watsonx.ai** | USD 81.28 | USD 191.91 | USD 1,422 |
| **Cloudflare Workers AI** | USD 66.92 | USD 104.11 | USD 730.17 |
| **Venice** | USD 113.40 | USD 210.00 | USD 1,512 |

For the support chatbot, the cheapest price (DeepInfra, USD 14.76 a month) saves USD 56.50 against the median (USD 71.26). For the coding agent the gap is USD 904.50 a month (81% lower).

## Which Llama 3.3 70B provider is cheapest for your traffic?

DeepInfra has the lowest input price (USD 0.10) and the lowest output price (USD 0.32), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

Llama 3.3 70B: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **DeepInfra** (no cache price) | USD 0.155 cheapest | USD 0.155 cheapest | USD 0.155 cheapest |
| **Novita AI** (no cache price) | USD 0.2013 | USD 0.2013 | USD 0.2013 |
| **AkashML** | USD 0.28 | USD 0.2425 | USD 0.2125 |
| **Parasail** | USD 0.29 | USD 0.2487 | USD 0.2157 |
| **GMI Cloud** (no cache price) | USD 0.375 | USD 0.375 | USD 0.375 |
| **Featherless** | USD 0.675 | USD 0.6262 | USD 0.5873 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 8 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

3 of 14 providers publish a cached-input price below the input price: AkashML (50% off), Parasail (50% off), Featherless (20% off). DeepInfra, Novita AI, GMI Cloud, CoreWeave Forge, Microsoft Azure and 6 more publish none, so cached tokens there bill at the input price.

Context windows differ: 131,072 tokens at DeepInfra, AkashML and GMI Cloud; 128,000 tokens at CoreWeave Forge and Venice; 32,768 tokens at Featherless; 12,288 tokens at Novita AI. Parasail, Microsoft Azure, Amazon Bedrock, Google Vertex AI, SambaNova and 2 more do not state one. The cheapest row is not always the one that fits a long prompt.

## What does Llama 3.3 70B cost in other languages?

The same text needs a different number of tokens in each language. With the Llama 3.3 70B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Llama 3.3 70B:

| Content | Input per 1M characters | Cheapest provider |
| --- | --- | --- |
| English | USD 0.022 | DeepInfra |
| Arabic MSA | USD 0.039 | DeepInfra |
| Hindi | USD 0.052 | DeepInfra |
| Chinese | USD 0.080 | DeepInfra |
| Code | USD 0.025 | DeepInfra |

From BroadRouter's [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/), which covers 15 languages and content types for every model we could match to a measured tokenizer.

## Published benchmark results

BroadNet did not run these benchmarks; results are as published by the Meta model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.

Published benchmark results for Llama 3.3 70B, with sources
| Benchmark | Result | Setting or note | Source |
| --- | --- | --- | --- |
| MMLU Pro (CoT) | 68.9 | 5-shot, chain of thought | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 |
| IFEval | 92.1 | not stated | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 |
| GPQA Diamond (CoT) | 50.5 | 0-shot, chain of thought | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 |
| HumanEval | 88.4 | 0-shot, pass@1 | [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), checked 2026-11-16 |
| GPQA Diamond | 0.474 | Setting as listed by Epoch (no suffix); Epoch run Llama-3.3-70B-Instruct, mean score on a 0 to 1 scale | [Epoch AI](https://epoch.ai/benchmarks/use-this-data), checked 2026-11-16 |

Epoch AI rows: [Epoch AI, Capabilities & benchmarking](https://epoch.ai/benchmarks/use-this-data), licensed [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

## Estimate your own bill

-   [LLM API cost calculator with Llama 3.3 70B preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=llama-3.3-70b-instruct): your traffic and cache rate, against any of 431 models.
-   [Llama 3 token counter](https://broadrouter.com/tools/llama-token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does Llama 3.3 70B compare with other Meta models?

The Meta models whose cheapest standard price is closest to Llama 3.3 70B's (USD 0.155 blended):

Meta models priced closest to Llama 3.3 70B
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [Llama 3.2 11B Vision Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-11b-vision-instruct/) | USD 0.16 | USD 0.16 | — | 3 |
| [Llama 4 Scout 17B 16E Instruct](https://broadrouter.com/llm-api-pricing/llama-4-scout/) | USD 0.10 | USD 0.30 | 1,048,576 | 6 |
| [Muse Glimmer 30B](https://broadrouter.com/llm-api-pricing/muse-glimmer-30b/) | USD 0.11 | USD 0.32 | 131,072 | 4 |
| [Llama 3.2 3B Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-3b-instruct/) | USD 0.0509 | USD 0.335 | 128,000 | 4 |
| [Llama 3 8B Instruct](https://broadrouter.com/llm-api-pricing/llama-3-8b-instruct/) | USD 0.0925 | USD 0.095 | 8,192 | 3 |
| [Llama 3.2 1B Instruct](https://broadrouter.com/llm-api-pricing/llama-3.2-1b-instruct/) | USD 0.027 | USD 0.201 | 32,768 | 3 |

Priced closest from other makers: [NVIDIA Nemotron 3 Super 120B A12B](https://broadrouter.com/llm-api-pricing/nemotron-3-super-120b-a12b/) (NVIDIA, USD 0.1563) · [Qwen3 235B A22B Instruct 2507 FP8](https://broadrouter.com/llm-api-pricing/qwen3-235b-a22b-2507/) (Qwen, USD 0.1531) · [gemma-4-31B-it-turbo](https://broadrouter.com/llm-api-pricing/gemma-4-31b-it-turbo/) (Google, USD 0.1525).

## Compare Llama 3.3 70B with

-   [Llama 4 Maverick vs Llama 3.3 70B](https://broadrouter.com/llm-api-pricing/compare/llama-4-maverick-vs-llama-3.3-70b-instruct/): API price side by side
-   [gpt-oss-120b vs Llama 3.3 70B](https://broadrouter.com/llm-api-pricing/compare/gpt-oss-120b-vs-llama-3.3-70b-instruct/): API price side by side
-   [Llama 3.3 70B vs Qwen2.5 72B](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-qwen2.5-72b-instruct/): API price side by side
-   [Llama 3.3 70B vs Gemma 4 26B A4B](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-gemma-4-26b-a4b-it/): API price side by side
-   [Llama 3.3 70B vs Llama 3.1 70B](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-llama-3.1-70b-instruct/): API price side by side

Also compared: [vs Llama 4 Maverick 17B 128E Instruct FP8](https://broadrouter.com/llm-api-pricing/compare/llama-4-maverick-vs-llama-3.3-70b-instruct/) · [vs OpenAI GPT OSS 120B](https://broadrouter.com/llm-api-pricing/compare/gpt-oss-120b-vs-llama-3.3-70b-instruct/) · [vs Qwen2.5-72B-Instruct](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-qwen2.5-72b-instruct/) · [vs Gemma 4 26B A4B](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-gemma-4-26b-a4b-it/) · [vs Llama 3.1 Instruct (70B)](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-llama-3.1-70b-instruct/).

[Every Llama 3.3 70B price comparison](https://broadrouter.com/llm-api-pricing/compare/#m-llama-3.3-70b-instruct) · [All model-vs-model price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

[All 431 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the Llama 3.3 70B API cost per token?

From USD 0.10 per 1M input tokens (USD 0.0000001 per token) and USD 0.32 per 1M output tokens (USD 0.00000032 per token) at the lowest standard prices we found. The median of 14 standard prices is USD 0.625 input and USD 0.72 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for Llama 3.3 70B?

Among the 14 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.155 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does Meta sell Llama 3.3 70B on its own API?

Meta does not sell Llama models through an API of its own: llama.com now redirects to Meta's developer site, whose Model API lists only Meta's Muse models. Llama is available only from third-party hosts. The lowest-priced host we checked is DeepInfra at USD 0.10 / USD 0.32 per 1M tokens.

### Does Llama 3.3 70B have cached input pricing?

3 of 14 standard prices include one. The lowest is USD 0.10 per 1M at AkashML; the median is USD 0.11. Providers without one bill cached input at the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

### What is the Llama 3.3 70B context window?

Up to 131,072 tokens. 4 standard prices come with less, down to 12,288 tokens (Novita AI, Featherless, CoreWeave Forge and Venice). Check the context column before you pick the cheapest row for long prompts. [Context window calculator](https://broadrouter.com/tools/context-window-calculator/).

### How much does a coding agent cost per month on Llama 3.3 70B?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 208.80 a month at DeepInfra, USD 1,113 at the median price and USD 1,512 at Venice. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=llama-3.3-70b-instruct).

### Is there a batch, flex or priority price for Llama 3.3 70B?

Yes: batch from Amazon Bedrock at USD 0.36 / USD 0.36; flex / spot from DeepInfra at USD 0.08 / USD 0.256 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

### Is Llama 3.3 70B free to use through an API?

No provider in our data lists a free price for Llama 3.3 70B as of 2026-11-15. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is Llama 3.3 70B open source, with open weights, and what is its licence?

Meta publishes the weights on Hugging Face as [`meta-llama/Llama-3.3-70B-Instruct`](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct), with gated access: Hugging Face asks you to request access and accept the terms before you download. The licence, as the [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) states it: Llama 3.3 Community License Agreement (custom commercial license). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Meta's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does Llama 3.3 70B have?

Total parameters, as the [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) states them: 70B. (checked 2026-11-16; BroadNet did not verify these figures.)

### Does Llama 3.3 70B support tool calling?

Yes, according to the [Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct): “LLaMA-3.3 supports multiple tool use formats.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.

### How do I call Llama 3.3 70B with the OpenAI SDK?

BroadNet does not serve Llama 3.3 70B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with `OpenAI(base_url=..., api_key=...)` and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: [DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/) (`https://api.deepinfra.com/v1/openai`, model `meta-llama/Llama-3.3-70B-Instruct-Turbo`). Each provider page quotes the provider's docs with a check date.

### How does Llama 3.3 70B score on benchmarks?

As published, [the Meta model card](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) reports 68.9 on MMLU Pro (CoT) and 92.1 on IFEval; [Epoch AI](https://epoch.ai/benchmarks/use-this-data) measured 0.474 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-llama-3.3-70b-instruct&utm_content=page-cta) ·

**Sources**

-   [AkashML: pricing (checked 2026-11-15)](https://akashml.com/models/llama-3-3-70b)
-   [Amazon Bedrock: pricing (checked 2026-11-14)](https://aws.amazon.com/bedrock/pricing/)
-   [Microsoft Azure: pricing (checked 2026-11-14)](https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/llama/)
-   [Cloudflare Workers AI: pricing (checked 2026-11-14)](https://developers.cloudflare.com/workers-ai/platform/pricing/)
-   [CoreWeave Forge: pricing (checked 2026-11-15)](https://coreweave.com/forge-pricing/inference-agents)
-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/meta-llama/Llama-3.3-70B-Instruct)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://console.gmicloud.ai/model/llm/llama-3-3-70b-instruct/d9755097-53db-4a09-bf63-f8150f4c39fb)
-   [Google Vertex AI: pricing (checked 2026-11-14)](https://cloud.google.com/model-garden/partner-models/pricing)
-   [IBM watsonx.ai: pricing (checked 2026-11-15)](https://www.ibm.com/products/watsonx-ai/pricing)
-   [Novita AI: pricing (checked 2026-11-14)](https://novita.ai/pricing)
-   [Parasail: pricing (checked 2026-11-14)](https://www.parasail.io/pricing)
-   [SambaNova: pricing (checked 2026-11-14)](https://cloud.sambanova.ai/plans/pricing)
-   [Venice: pricing (checked 2026-11-15)](https://docs.venice.ai/pricing)
-   [Meta developer docs (checked 2026-11-14)](https://dev.meta.ai/docs/overview)
