# Llama-3.3-70B-Instruct API pricing

No price from the maker itself is on record for Llama-3.3-70B-Instruct. The lowest of 40 providers is NanoGPT: $0.05 per 1M input tokens and $0.23 per 1M output tokens (as of 2026-11-12). Context window: 128K tokens, up to 4.1K output tokens per request.

- Type: Text
- Context: 128K
- Max output: 4.1K
- Released: 2024-12-06
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [NanoGPT](https://docs.nano-gpt.com) | meta-llama/llama-3.3-70b-instruct | $0.05 | $0.23 | $0.025 | Lowest |
| [Meganova](https://docs.meganova.ai) | meta-llama/Llama-3.3-70B-Instruct | $0.1 | $0.3 | — |  |
| [Deep Infra](https://deepinfra.com/models) | meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.1 | $0.32 | — |  |
| [Eden AI](https://docs.edenai.co) | deepinfra/meta-llama/Llama-3.3-70B-Instruct | $0.1 | $0.32 | — |  |
| [Kilo Gateway](https://kilo.ai) | meta-llama/llama-3.3-70b-instruct | $0.1 | $0.32 | — |  |
| [Helicone](https://helicone.ai/models) | llama-3.3-70b-instruct | $0.13 | $0.39 | — |  |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | llama-3.3-70b-instruct | $0.135 | $0.4 | — |  |
| [LLM Gateway](https://llmgateway.io/docs) | novita/llama-3.3-70b-instruct | $0.135 | $0.4 | — |  |
| [Novita AI](https://novita.ai/docs/guides/introduction) | meta-llama/llama-3.3-70b-instruct | $0.135 | $0.4 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | meta/llama-3.3-70b-instruct | $0.22 | $0.5 | $0.11 |  |
| [STACKIT](https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models) | cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic | $0.53 | $0.76 | — |  |
| [Helicone](https://helicone.ai/models) | llama-3.3-70b-versatile | $0.59 | $0.79 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | meta-llama/Llama-3.3-70B-Instruct | $0.59 | $0.79 | — |  |
| [OpenRouter](https://openrouter.ai/models) | meta-llama/llama-3.3-70b-instruct | $0.71 | $0.71 | $0.71 |  |
| [CoreWeave](https://docs.wandb.ai/inference) | meta-llama/Llama-3.3-70B-Instruct | $0.71 | $0.71 | $0.71 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | meta/llama-3.3-70b | $0.72 | $0.72 | — |  |
| [Eden AI](https://docs.edenai.co) | ionos/meta-llama/Llama-3.3-70B-Instruct | $0.723255 | $0.723255 | — |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | llama-3.3-70b-instruct | $0.724 | $0.724 | — |  |
| [OVHcloud AI Endpoints](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//) | meta-llama-3_3-70b-instruct | $0.74 | $0.74 | — |  |
| [watsonx.ai](https://www.ibm.com/docs/en/watsonx/saas?topic=solutions-supported-foundation-models) | meta-llama/llama-3-3-70b-instruct | $0.7526 | $0.7526 | — |  |
| [IO.NET](https://io.net/docs/guides/intelligence/io-intelligence) | meta-llama/Llama-3.3-70B-Instruct | $0.5466 | $1.0226 | $0.2733 |  |
| [SambaNova](https://docs.sambanova.ai/cloud/docs/get-started/supported-models) | Meta-Llama-3.3-70B-Instruct | $0.6 | $1.2 | — |  |
| [Neon](https://neon.com/docs) | meta-llama-3-3-70b-instruct | $0.5 | $1.5 | — |  |
| [Eden AI](https://docs.edenai.co) | scaleway/llama-3.3-70b-instruct | $1.00143 | $1.00143 | — |  |
| [Scaleway](https://www.scaleway.com/en/docs/generative-apis/) | llama-3.3-70b-instruct | $1.00935 | $1.00935 | — |  |
| [evroc](https://docs.evroc.com/products/think/overview.html) | nvidia/Llama-3.3-70B-Instruct-FP8 | $1.15 | $1.15 | — |  |
| [Eden AI](https://docs.edenai.co) | greenpt/llama-3.3-70b-instruct | $1.22397 | $1.22397 | — |  |
| [GreenPT](https://docs.greenpt.ai) | llama-3.3-70b-instruct | $1.254 | $1.254 | — |  |
| [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/models/) | @cf/meta/llama-3.3-70b-instruct-fp8-fast | $0.293 | $2.253 | — |  |
| [AI/ML API](https://docs.aimlapi.com) | meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.76176 | $2.383674 | — |  |
| [Prime Inference](https://docs.primeintellect.ai/inference/overview) | meta-llama/llama-3.3-70b-instruct | $1.04 | $2.253 | — |  |
| [Venice AI](https://docs.venice.ai) | llama-3.3-70b | $0.7 | $2.8 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | TEE/llama3-3-70b | $1.75 | $2.75 | $1.75 |  |
| [Tinfoil](https://docs.tinfoil.sh) | llama3-3-70b | $1.75 | $2.75 | — |  |
| [CloudFerro Sherlock](https://docs.sherlock.cloudferro.com/) | meta-llama/Llama-3.3-70B-Instruct | $2.92 | $2.92 | — |  |
| [Crusoe](https://docs.crusoecloud.com/managed-inference/overview) | meta-llama/Llama-3.3-70B-Instruct | $0.25 | $0.75 | $0.13 | Deprecated |
| [Abacus](https://abacus.ai/help/api) | llama-3.3-70b-versatile | $0.59 | $0.79 | — | Deprecated |
| [Abacus](https://abacus.ai/help/api) | meta-llama/Meta-Llama-3.3-70B-Instruct | $0.59 | $0.79 | — | Deprecated |
| [Groq](https://console.groq.com/docs/models) | llama-3.3-70b-versatile | $0.59 | $0.79 | — | Deprecated |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | — | Deprecated |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | — | Deprecated |
| [OCI Generative AI](https://docs.oracle.com/en-us/iaas/Content/generative-ai/pretrained-models.htm) | meta.llama-3.3-70b-instruct | $0.72 | $0.72 | — | Deprecated |
| [Together AI](https://docs.together.ai/docs/serverless-models) | meta-llama/Llama-3.3-70B-Instruct-Turbo | $1.04 | $1.04 | — | Deprecated |
| [Regolo AI](https://docs.regolo.ai/) | llama-3.3-70b-instruct | $0.6 | $2.7 | — | Deprecated |
| [Pendra](https://pendra.ai/docs/integrations/opencode) | llama3.3:70b | $0 | $0 | — |  |
| [Poe](https://creator.poe.com/docs/external-applications/openai-compatible-api) | cerebras/llama-3.3-70b-cs | — | — | — | Deprecated |
| [Snowflake Cortex](https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api) | snowflake-llama3.3-70b | — | — | — |  |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/meta/llama-3.3-70b-instruct/