Llama 3.1 8B Instruct
An update to Meta Llama 3 8B Instruct that includes an expanded 128K context length, multilinguality and improved reasoning capabilities.
text → text · made by Meta
Sold by 34 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock 0 ways | $0.11per Mtok in$0.11per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | batch | $0.11per Mtok in$0.11per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Databricks cloud | standard | $0.15per Mtok in$0.45per Mtok out$0.15per Mtok cached$0.15per Mtok cache writeraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock cloud | standard | $0.22per Mtok in$0.22per Mtok outmodels.dev · read 2026-10-31 |
| Snowflake Cortex cloud | standard | $0.24per Mtok in$0.24per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Microsoft Azure AI 0 ways | $0.3per Mtok in$0.61per Mtok out | |
| Microsoft Azure AI cloudnot on the seller's list today | standard | $0.3per Mtok in$0.61per Mtok outraw.githubusercontent.com · read 2026-09-22 |
| Oracle Cloud Infrastructure cloud | standard | $0.72per Mtok in$0.72per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| DeepInfra aggregator | standard | $0.02per Mtok in$0.05per Mtok outapi.deepinfra.com · read 2026-08-25 |
| Hugging Face Inference Providers 4 ways | $0.06per Mtok in$0.06per Mtok out | |
| Hugging Face Inference Providers aggregator | deepinfra | $0.02per Mtok in$0.05per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | novita | $0.02per Mtok in$0.05per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Hugging Face Inference Providers aggregator | standard | $0.06per Mtok in$0.06per Mtok outmodels.dev · read 2026-10-31 |
| Hugging Face Inference Providers aggregator | nscale | $0.06per Mtok in$0.06per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI aggregator | standard | $0.02per Mtok in$0.05per Mtok outapi.novita.ai · read 2026-09-02 |
| Novita AI aggregatornot on the seller's list today | alt | $0.02per Mtok in$0.05per Mtok outapi.novita.ai · read 2026-08-25 |
| OpenRouter 6 ways | $0.05per Mtok in$0.08per Mtok out$0.025per Mtok cached | |
| OpenRouter aggregator | deepinfra/fp8 | $0.02per Mtok in$0.04per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | novita/fp8 | $0.02per Mtok in$0.05per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | standard | $0.05per Mtok in$0.08per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-10-29 |
| OpenRouter aggregator | groq | $0.05per Mtok in$0.08per Mtok out$0.025per Mtok cachedopenrouter.ai · read 2026-10-28 |
| OpenRouter aggregator | cloudflare/fp8 | $0.15per Mtok in$0.29per Mtok outopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | coreweave/bf16 | $0.22per Mtok in$0.22per Mtok out$0.22per Mtok cachedopenrouter.ai · read 2026-08-25 |
| Lambda aggregator | standard | $0.025per Mtok in$0.04per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| ElectronHub 0 ways | $0.03per Mtok in$0.05per Mtok out | |
| ElectronHub aggregatornot on the seller's list today | standard | $0.03per Mtok in$0.05per Mtok outapi.electronhub.ai · read 2026-09-09 |
| Nscale aggregator | standard | $0.03per Mtok in$0.03per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Cloudflare 0 ways | $0.045per Mtok in$0.38per Mtok out | |
| Cloudflare aggregatornot on the seller's list today | fp8-fast | $0.045per Mtok in$0.38per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Cloudflare aggregatornot on the seller's list today | fp8-fast sandbox | $0.045per Mtok in$0.38per Mtok outdevelopers.cloudflare.com · read 2026-08-25 |
| Groq aggregator | standard | $0.05per Mtok in$0.08per Mtok outmodels.dev · read 2026-10-31 |
| Nous Research aggregator | standard | $0.05per Mtok in$0.08per Mtok out$0.025per Mtok cachedinference-api.nousresearch.com · read 2026-10-29 |
| Requesty aggregator | novita | $0.05per Mtok in$0.05per Mtok out$0.05per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Cerebras aggregator | standard | $0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| FriendliAI 0 ways | $0.1per Mtok in$0.1per Mtok out | |
| FriendliAI aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.1per Mtok outraw.githubusercontent.com · read 2026-09-14 |
| SambaNova Cloud 0 ways | $0.1per Mtok in$0.2per Mtok out | |
| SambaNova Cloud aggregatornot on the seller's list today | standard | $0.1per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-09-22 |
| Hyperbolic aggregator | standard | $0.12per Mtok in$0.3per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Featherless AI aggregator | standard | $0.2per Mtok in$0.32per Mtok outapi.featherless.ai · read 2026-09-23 |
| Together AI aggregator | standard | $0.2per Mtok in$0.2per Mtok outraw.githubusercontent.com · read 2026-10-31 |
| Vercel AI Gateway aggregator | standard | $0.22per Mtok in$0.22per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
Measured 14 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 18thof 170 | Gsm8k — Epoch AI | EM | 0.824 |
| 34thof 41 | Balrog — Epoch AI | Average progress | 0.151 |
| 48thof 136 | Bool q — Epoch AI | Score | 82.8 |
| 49thof 113 | Piqa — Epoch AI | Score | 81.2 |
| 86thof 108 | Math level 5 — Epoch AI | mean_score | 22.876 |
| 136thof 217 | Mmlu — Epoch AI | EM | 0.561 |
| 161stof 163 | Artificial Analysis · Coding Index | Index | 5.4 |
| 173rdof 173 | Weirdml — Epoch AI | Accuracy | 1.73 |
| 194thof 197 | Lmca — Epoch AI | Score | 5.37 |
| 211thof 260 | Critpt — Epoch AI | Accuracy | 0 |
| 217thof 235 | Dtbench — Epoch AI | Accuracy | 50.93 |
| 233rdof 235 | Scicode — Epoch AI | Score | 13.194 |
| 294thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 1.667 |
| 313thof 326 | GPQA Diamond | mean_score | 26.957 |
About
Llama 3.1 8B Instruct — a text model from Meta, sold by 18 companies from $0.02 in and $0.05 out per million tokens, placed 18th of 170 on Gsm8k — Epoch AI.
It takes text and returns text, with a context window of 32,768 tokens. It was published in 2024, trained on material up to December 2023. Its sellers say it can call a tool. The catalogue files it under reasoning. Eighteen companies sell it. The cheapest is $0.02 in and $0.05 out per million tokens at DeepInfra. Beside the standard rate there are separately routed and regional lanes. It has been measured on 14 boards, and stands best at 18th of 170 on Gsm8k — Epoch AI.
Every current figure
- Maker
- Meta
- Register
- model
- Takes
- text
- Returns
- text
- Context
- 32,768 tokens
- Published
- 2024
- Knowledge to
- December 2023
- Parameters
- 8 billion
- Licence
- not read
- Sellers
- 18
- Maker's own price
- not read
- Price
- $0.02 in and $0.05 out per million tokens — DeepInfra
- Boards
- 14
- Best place
- 18th of 170 — Gsm8k — Epoch AI
Known as 38 names
Meta-Llama-3.1-8B-InstructLlama 3.1 8Bmeta.llama3-1-8b-instruct-v1:0@cf/meta/llama-3.1-8b-instruct-fp8-fastmeta-llama/Meta-Llama-3.1-8B-InstructCirrascale/Meta-Llama-3.1-8B-InstructCrystalcareai/Meta-llama-3.1-8b-instructCrystalcareai/meta-llama-3.1-8bDeSTA-ntu/Llama-3.1-8B-InstructNousResearch/Meta-Llama-3.1-8BNousResearch/Meta-Llama-3.1-8B-InstructOpenPipe/Llama-3.1-8B-InstructRedHatAI/Llama-3.1-8B-InstructSillyTilly/Meta-Llama-3.1-8BSillyTilly/Meta-Llama-3.1-8B-InstructSmallDoge/Llama3.1-8b-110kVityaVitalich/Llama3.1-8bVityaVitalich/Llama3.1-8b-instructaifeifei798/Meta-Llama-3.1-8B-Instructcamenduru/Meta-Llama-3.1-8B-Instructcobrokerai/llama-3-1-8blivil/llama3.1-8b-instructmeta-llama/Llama-3.1-8Bmeta-llama/Llama-3.1-8B-Instructmeta-llama/Meta-Llama-3.1-8Bmombip/Meta-Llama-3.1-8B-Instructmylesgoose/Llama-3.1-8B-InstructnreHieW/Llama-3.1-8B-Instructphamtungthuy/Llama-3.1-8B-Instructtanliboy/Meta-Llama-3.1-8B-Instructunsloth/Llama-3.1-8Bunsloth/Llama-3.1-8B-Instructunsloth/Meta-Llama-3.1-8Bunsloth/Meta-Llama-3.1-8B-Instructzgrgr/Meta-Llama-3.1-8B-Instructllama-3.1-8b-instantnovita/meta-llama/llama-3.1-8b-instructmeta/llama-3.1-8b