Listings
All listings for Llama 3.3 70B Instruct
Every priced listing we track for this model. Back to Llama 3.3 70B Instruct
| Provider | Max Input Tokens | Input $/1M | Output $/1M | Tok/s | Latency |
|---|---|---|---|---|---|
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 128K | $0.72batch $0.36 | $0.72batch $0.36 | β | β |
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 128K | $0.71 | $0.71 | β | β |
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 128K | $0.72batch $0.36 | $0.72batch $0.36 | β | β |
Data from 302.ai | 128K | $0.90 | $0.90 | β | β |
Data from AIHubMix Fields by sourceFrom AIHubMix: max output tokens | 131K | $0.60 | $1.20 | β | β |
Data from Cortecs EU Router Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | β¬0.65β $0.7133 USD (compared by USD value) | β¬0.65β $0.7133 USD (compared by USD value) | β | β |
Data from Models.dev | 131K | $0.10 | $0.32 | β | β |
Data from Models.dev | 128K | $0.7144 | $0.7144 | β | β |
Data from Models.dev | 128K | $0.9891 | $0.9891 | β | β |
Data from EURouter | 128K | $0.71 | $0.71 | β | β |
Data from FlowDot | 66K | $0.00 | $0.00 | β | β |
Data from FlowDot | 131K | $2.00 | $2.00 | β | β |
Data from Hugging Face Inference Providers | 131K | $0.10 | $0.32 | β | β |
Data from Hugging Face Inference Providers Fields by sourceFrom GenAI Prices: offering name | 12K | $0.135 | $0.40 | β | β |
Data from Hugging Face Inference Providers | 131K | $0.20 | $0.52 | β | β |
Data from Hugging Face Inference Providers | 131K | $0.22 | $0.50 | β | β |
Data from GenAI Prices | 131K | $0.25 | $0.75 | β | β |
Data from Hugging Face Inference Providers | 24K | $0.293 | $2.253 | β | β |
Data from GenAI Prices | 131K | $0.40 | $0.40 | β | β |
Data from GenAI Prices | 131K | $0.40 | $0.40 | β | β |
Data from Hugging Face Inference Providers Fields by sourceFrom GenAI Prices: offering name | 131K | $0.59 | $0.79 | β | β |
Data from Models.dev | 131K | $0.59 | $0.79 | β | β |
Data from GenAI Prices | 131K | $0.60 | $1.20 | β | β |
Data from Hugging Face Inference Providers | 128K | $0.71 | $0.71 | β | β |
Data from Hugging Face Inference Providers | 131K | $0.72 | $0.72 | β | β |
Data from GenAI Prices | 131K | $0.74 | $0.74 | β | β |
Data from GenAI Prices | 131K | $0.88 | $0.88 | β | β |
Data from GenAI Prices | 131K | $0.90 | $0.90 | β | β |
Data from Kilo AI Gateway Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.10 | $0.32 | β | β |
Data from LLMGateway | βNot published by the provider | $0.13 | $0.40 | β | β |
Data from LLMGateway | βNot published by the provider | $0.135 | $0.40 | β | β |
Data from LLMGateway | βNot published by the provider | $0.85 | $1.20 | β | β |
Data from MegaNova Fields by sourceFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | $0.10 | $0.30 | β | β |
Data from NanoGPT Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | $0.05cache read $0.025 | $0.23 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.105 | $0.336 | 30 | 766ms |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.21cache read $0.105 | $0.546 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: Provider terms restrict distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.231cache read $0.1155 | $0.525 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.3077 | $2.3657 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: Provider terms restrict distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.6195cache read $0.3098 | $0.8295 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.7455 | $0.7455 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: License permits distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.7455 | $0.7455 | β | β |
zero retention, per NanoGPTData privacy: zero data retention Β· prompts not retained Β· no training on prompts
Source: NanoGPT policy notesprivacy: zdr; distillation: Provider terms restrict distillation β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $0.756 | $0.756 | β | β |
TEEThe provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data. Data from NanoGPT Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $1.75 | $2.75 | β | β |
TEEThe provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data. policy notesdistillation: Distillation status unknown β NanoGPT privacy policy Data from NanoGPT | βNot published by the provider | $1.8375 | $2.8875 | 35.4 | 5,862ms |
Data from Nous Portal Inference Gateway | 131K | $0.71 | $0.71 | β | β |
Data from Helicone Costs | βNot published by the provider | $0.00 | $0.00 | β | β |
Data from OpenRouter | 131K | $0.10 | $0.32 | 13 | 594ms |
Data from OpenRouter | 131K | $0.20cache read $0.10 | $0.52 | 29 | 736ms |
Data from OpenRouter | 131K | $0.22cache read $0.11 | $0.50 | 42 | 861ms |
Data from OpenRouter | 24K | $0.293 | $2.253 | 48 | 962ms |
Data from OpenRouter | 131K | $0.59cache read $0.295 | $0.79 | 210.5 | 422ms |
Data from OpenRouter | 128K | $0.71 | $0.71 | 88 | 141ms |
Data from OpenRouter Fields by sourceFrom GenAI Prices: offering nameFrom Models.dev: supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.71 | $0.71 | β | β |
Data from OpenRouter | 131K | $0.72 | $0.72 | 110 | 359.5ms |
Data from OpenRouter | 128K | $0.72 | $0.72 | β | β |
Data from OpenRouter | 128K | $0.72 | $0.72 | β | β |
TEEThe provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data. Data from RedPill | 131K | $2.00 | $2.00 | β | β |
Data from Requesty | 131K | $0.23 | $0.40 | β | β |
Data from Requesty | 131K | $0.39 | $0.39 | β | β |
Data from TokenMix Fields by sourceFrom TokenMix Pricing: currency, last updated, unit, input tokens, output tokens | βNot published by the provider | $0.6975 | $0.6975 | β | β |
policy notesAI Gateway uses zero data retention by default β Vercel AI Gateway security & compliance documentation
It permanently deletes your prompts and responses after requests complete. β Vercel AI Gateway security & compliance documentation
requests only route to providers with verified ZDR agreements β Vercel AI Gateway security & compliance documentation
The provider allowlist lets team owners restrict which AI providers can serve requests through AI Gateway β Vercel AI Gateway security & compliance documentation
Vercel may store, process and transmit your information outside of your country of residence, which may have different data protection laws and may not offer the same level of protection or guarantees as in your country or the country where you initially provided the information. β Vercel privacy policy
Sources: Vercel AI Gateway security & compliance documentation, Vercel privacy policy Data from Vercel AI Gateway Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports function calling, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.72 | $0.72 | β | β |
Data from WaveSpeed AI | 131K | $0.72cache read $0.295 | $0.72 | β | β |
Data from ZenMux | 128K | $0.60 | $1.20 | β | β |
Data from Models.dev | 131K | $0.59 | $0.79 | β | β |
Data from Akash | 131K | $0.20 | $0.52 | β | β |
Data from Apertus LLM Hosting | βNot published by the provider | β¬0.804β $0.8823 USD (compared by USD value) | β¬0.804β $0.8823 USD (compared by USD value) | β | β |
Data from GenAI Prices | βNot published by the provider | $0.45 | $0.45 | β | β |
Data from GenAI Prices Fields by sourceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, max input tokens, max output tokens | 128K | $0.85 | $1.20 | β | β |
Data from Models.dev | 70K | $2.92 | $2.92 | β | β |
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports vision, supports image input, cache-read price | 131K | $0.20cache read $0.13 | $0.20 | β | β |
Data from LiteLLM | 128K | $0.50 | $1.50cache write $0.50 | β | β |
Data from LiteLLM | 131K | $0.23 | $0.40 | β | β |
Data from Featherless | 33K | $0.65 | $0.75 | β | β |
Data from LiteLLM | 131K | $0.90 | $0.90 | β | β |
Data from flex.ai API | 131K | $0.22 | $0.50 | β | β |
Data from flex.ai Pricing | 128K | $0.22cache read $0.033 | $0.50 | β | β |
Data from LiteLLM | 131K | $0.25 | $0.75 | β | β |
Data from LiteLLM | 128K | $0.65 | $0.65 | β | β |
Data from Models.dev | 100K | $1.254 | $1.254 | β | β |
Data from Hyperbolic Fields by sourceFrom LiteLLM: offering name, max input tokens, max output tokens, supports parallel function calling, supports tool choice, supports system messages, max input tokens, max output tokens | 131K | $0.40 | $0.40 | β | β |
Data from IO Intelligence (io.net) Fields by sourceFrom Models.dev: max completion tokens, supported output modalities, supports reasoning, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 128K | $0.4786cache read $0.2393 | $1.0946 | 50.719 | 487.98ms |
Data from LiteLLM | 131K | $0.12 | $0.30 | β | β |
Data from Models.dev | 131K | $0.135 | $0.40 | β | β |
Data from Models.dev | 131K | $0.22cache read $0.11 | $0.50 | β | β |
Data from LiteLLM | 131K | $0.13 | $0.40 | β | β |
Data from Models.dev | 128K | $0.50 | $1.50 | β | β |
Data from Novita AI Fields by sourceFrom GenAI Prices: offering nameFrom LiteLLM: max input tokens, max output tokens, supports function calling, supports parallel function calling, supports tool choice, supports system messages, supports response schema, max input tokens, max output tokensFrom Models.dev: max completion tokens, supports reasoning, supports vision, supports image input | 12K | $0.135 | $0.40 | β | β |
Data from LiteLLM | βNot published by the provider | $0.20 | $0.20 | β | β |
Data from Models.dev | 128K | $0.0553 | $0.2542 | β | β |
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 128K | $0.72 | $0.72 | β | β |
Data from OVH Cloud Fields by sourceFrom GenAI Prices: offering nameFrom LiteLLM: max input tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, max input tokens, max output tokensFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 131K | $0.74 | $0.74 | β | β |
TEEThe provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data. Data from Models.dev | 131K | $2.00 | $2.00 | β | β |
Data from Models.dev | 131K | $1.04 | $2.253 | β | β |
Data from Models.dev | 128K | $0.60 | $2.70 | β | β |
Data from SambaNova API Fields by sourceFrom LiteLLM: max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, supports tool choice, supports response schema, max input tokens, max output tokens | 131K | $0.60 | $1.20 | β | β |
Data from Scaleway API Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, supports function calling, max input tokens, max output tokens, currency, last updated, input tokens, output tokensFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image inputFrom Scaleway Model as a Service: is available, regions | 128K | $0.90 | $0.90 | β | β |
Data from Simplismart Pricing | βNot published by the provider | $0.74 | β | β | β |
Data from LiteLLM | 128K | $0.72 | $0.72 | β | β |
TEEThe provider's listing says this runs in an attested confidential-computing enclave (a trusted execution environment), where the provider can't read your data. Data from Tinfoil Fields by sourceFrom Models.dev: max completion tokens, supported input modalities, supported output modalities, supports system messages, supports vision, max input tokens, max output tokens, supports image input | 131K | $1.75 | $2.75 | β | β |
private, per Venice.aiData privacy: private
Source: Venice.ai policy notesprivacy classification: private β Venice privacy documentation Data from Venice.ai | 128K | $0.70 | $2.80 | β | β |
Data from LiteLLM | 128K | $0.72 | $0.72 | β | β |
Data from Weights & Biases Inference Fields by sourceFrom LiteLLM: offering name, context length, max input tokens, max output tokens, supported input modalities, supported output modalities, max input tokens, max output tokens, currency, last updated, input tokens, output tokensFrom Models.dev: max completion tokens, supports function calling, supports reasoning, supports system messages, supports vision, supports image input, cache-read price | 128K | $0.71 | $0.71 | β | β |
Data from LiteLLM Fields by sourceFrom Models.dev: max completion tokens, supports reasoning, supports system messages, supports vision, supports image input | 131K | $0.7526 | $0.7526 | β | β |
16 listings without a price are hidden.
Select any dotted value, label or icon to see where it comes from and how it is measured. How this data works