Llama 3.3 70B Instruct
Where performance meets efficiency.
text → text · made by Meta
$0.1→$0.32per Mtok in / out
Nous Research · 29 sellers
Sold by 54 ways
| Seller | Lane | Rate |
|---|---|---|
| Crusoe cloud | standard | $0.25per Mtok in$0.75per Mtok out$0.13per Mtok cachedmodels.dev · read 2026-09-16 |
| AWS Bedrock 0 ways | $0.36per Mtok in$0.36per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | batch | $0.36per Mtok in$0.36per Mtok outaws.amazon.com · read 2026-08-24 |
| Google Vertex AI 0 ways | $0.36per Mtok in$0.36per Mtok out | |
| Google Vertex AI cloudnot on the seller's list today | batch | $0.36per Mtok in$0.36per Mtok outcloud.google.com · read 2026-08-24 |
| Databricks cloud | standard | $0.5per Mtok in$1.5per Mtok out$0.5per Mtok cached$0.5per Mtok cache writeraw.githubusercontent.com · read 2026-09-16 |
| DigitalOcean cloud | standard | $0.65per Mtok in$0.65per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $0.71per Mtok in$0.71per Mtok outmodels.dev · read 2026-09-16 |
| AWS Bedrock cloud | standard | $0.72per Mtok in$0.72per Mtok outaws.amazon.com · read 2026-08-24 |
| Google Vertex AI cloud | standard | $0.72per Mtok in$0.72per Mtok outcloud.google.com · read 2026-08-24 |
| Oracle Cloud Infrastructure cloud | standard | $0.72per Mtok in$0.72per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Snowflake Cortex cloud | standard | $0.72per Mtok in$0.72per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| IBM watsonx cloud | standard | $0.75per Mtok in$0.75per Mtok outmodels.dev · read 2026-09-16 |
| IBM watsonx.ai cloud | standard | $0.75per Mtok in$0.75per Mtok outibm.com · read 2026-08-25 |
| DeepInfra aggregatornot on the seller's list today | turbo | $0.1per Mtok in$0.32per Mtok outdeepinfra.com · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.23per Mtok in$0.4per Mtok outapi.deepinfra.com · read 2026-09-01 |
| Nous Research aggregator | standard | $0.1per Mtok in$0.32per Mtok out$0.57per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 14 ways | $0.1per Mtok in$0.32per Mtok out$0.71per Mtok cached | |
| OpenRouter aggregator | standard | $0.1per Mtok in$0.32per Mtok out$0.71per Mtok cachedopenrouter.ai · read 2026-09-03 |
| OpenRouter aggregator | deepinfra/turbo | $0.1per Mtok in$0.32per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | nebius/fp8 | $0.13per Mtok in$0.4per Mtok outopenrouter.ai · read 2026-09-01 |
| OpenRouter aggregator | novita/bf16 | $0.14per Mtok in$0.4per Mtok outopenrouter.ai · read 2026-08-27 |
| OpenRouter aggregator | akashml/fp8 | $0.2per Mtok in$0.52per Mtok out$0.1per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | parasail/fp8 | $0.22per Mtok in$0.5per Mtok out$0.11per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | crusoe/bf16 | $0.25per Mtok in$0.75per Mtok out$0.13per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | cloudflare/fp8 | $0.29per Mtok in$2.25per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | sambanova-turbo | $0.45per Mtok in$0.9per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | groq | $0.59per Mtok in$0.79per Mtok out$0.29per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | coreweave/fp16 | $0.71per Mtok in$0.71per Mtok out$0.71per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex | $0.72per Mtok in$0.72per Mtok outopenrouter.ai · read 2026-08-26 |
| OpenRouter aggregator | google-vertex/us-central1 | $0.72per Mtok in$0.72per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | together | $1.04per Mtok in$1.04per Mtok outopenrouter.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.12per Mtok in$0.4per Mtok outapi.electronhub.ai · read 2026-09-09 |
| Hyperbolic aggregator | standard | $0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| IO.NET aggregator | standard | $0.13per Mtok in$0.38per Mtok out$0.065per Mtok cached$0.26per Mtok cache writemodels.dev · read 2026-09-16 |
| Inference.net aggregator | standard | $0.13per Mtok in$0.4per Mtok outapi.inference.net · read 2026-09-16 |
| Nebius Token Factory aggregator | standard | $0.13per Mtok in$0.4per Mtok outtokenfactory.nebius.com · read 2026-08-25 |
| Requesty 3 ways | $0.13per Mtok in$0.4per Mtok out$0.13per Mtok cached | |
| Requesty aggregator | nebius | $0.13per Mtok in$0.4per Mtok out$0.13per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | deepinfra | $0.23per Mtok in$0.4per Mtok out$0.23per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | novita | $0.39per Mtok in$0.39per Mtok out$0.39per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Hugging Face Inference Providers 5 ways | $0.59per Mtok in$0.79per Mtok out | |
| Hugging Face Inference Providers aggregator | novita | $0.14per Mtok in$0.4per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.59per Mtok in$0.79per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | ovhcloud | $0.74per Mtok in$0.74per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | scaleway | $1.03per Mtok in$1.03per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | together | $1.04per Mtok in$1.04per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI aggregator | standard | $0.14per Mtok in$0.4per Mtok outapi.novita.ai · read 2026-08-25 |
| Lambda aggregator | standard | $0.2per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Nscale aggregator | standard | $0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Cloudflare 0 ways | $0.29per Mtok in$2.25per Mtok out | |
| Cloudflare aggregatornot on the seller's list today | standard | $0.29per Mtok in$2.25per Mtok outmodels.dev · read 2026-08-27 |
| Cloudflare aggregatornot on the seller's list today | fp8-fast | $0.29per Mtok in$2.25per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | fp8-fast sandbox | $0.29per Mtok in$2.25per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Groq aggregator | standard | $0.59per Mtok in$0.79per Mtok outmodels.dev · read 2026-09-16 |
| SambaNova Cloud aggregator | standard | $0.6per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Venice AI aggregator | standard | $0.7per Mtok in$2.8per Mtok outmodels.dev · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $0.72per Mtok in$0.72per Mtok outvercel.com · read 2026-08-25 |
| Cerebras aggregator | standard | $0.85per Mtok in$1.2per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Together AI aggregator | standard | $1.04per Mtok in$1.04per Mtok outdocs.together.ai · read 2026-08-24 |
Measured 17 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 8thof 217 | Mmlu — Epoch AI | EM | 0.863 |
| 21stof 36 | Balrog — Epoch AI | Average progress | 0.23 |
| 30thof 54 | Live bench — Epoch AI | Global average | 50.16 |
| 50thof 81 | Forecastbench — Epoch AI | Overall score | 58.6 |
| 71stof 108 | Math level 5 — Epoch AI | mean_score | 41.597 |
| 93rdof 123 | Lmca — Epoch AI | Score | 17.52 |
| 96thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.199 |
| 121stof 161 | Dtbench — Epoch AI | Accuracy | 59.47 |
| 153rdof 177 | Critpt — Epoch AI | Accuracy | 0 |
| 157thof 168 | Scicode — Epoch AI | Score | 26.042 |
| 160thof 170 | Weirdml — Epoch AI | Accuracy | 14.44 |
| 169thof 184 | Artificial Analysis · Coding Index | Index | 11.9 |
| 227thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index | 8 |
| 243rdof 313 | GPQA Diamond | mean_score | 47.443 |
| 250thof 402 | LMArena · Text | Score (Elo) | 1318 |
| 258thof 290 | OTIS Mock AIME 2024-2025 | mean_score | 5.139 |
| 543rdof 656 | Epoch capabilities index — Epoch AI | ECI Score | 127.32 |
About
Llama 3.3 70B Instruct — a text model from Meta, sold by 29 companies from $0.1 in and $0.32 out per million tokens, placed 8th of 217 on Mmlu — Epoch AI.
It takes text and returns text, with a context window of 128,000 tokens. It was published in November 2024, trained on material up to December 2023. Its sellers say it can call a tool. The catalogue files it under reasoning and agents. 29 companies sell it. The cheapest is $0.1 in and $0.32 out per million tokens at Nous Research. Beside the standard rate there are separately routed and regional lanes. It has been measured on 17 boards, and stands best at 8th of 217 on Mmlu — Epoch AI.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 128,000 tokens
- Published
- November 2024
- Knowledge to
- December 2023
- Parameters
- 71 billion
- Licence
- not read
- Sellers
- 29
- Maker's own price
- not read
- Price
- $0.1 in and $0.32 out per million tokens — Nous Research
- Boards
- 17
- Best place
- 8th of 217 — Mmlu — Epoch AI
Known as 11 names
Llama 3.3 70Bmeta.llama3-3-70b-instruct-v1:0@cf/meta/llama-3.3-70b-instruct-fp8-fastmeta-llama/Llama-3.3-70B-Instructllama-3.3-70b-versatilellama-3-3-70b-instructdeepinfra/meta-llama/Llama-3.3-70B-Instructnebius/meta-llama/Llama-3.3-70B-Instructnovita/meta-llama/llama-3.3-70b-instructMeta-Llama-3.3-70B-Instructmeta/llama-3.3-70b