Skip to main content

Llama 3.1 70B Instruct

meta-llama/Llama-3.1-70B-Instruct is a Hugging Face model based on meta-llama/Meta-Llama-3.1-70B with tags including facebook, meta, pytorch, llama.

Input / output price
$0.40 / $0.40 per 1M
Context
131K tokens
Released
Jul 23, 2024
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "llama-3.1-70b-instruct".

Read docs

Providers

5 routes from 4 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Bedrockbedrock/llama-3.1-70b-instruct
$0.72/M$0.72/M
Bedrockbedrock/meta.llama3-1-70b-instruct-v1:0
$0.72/M$0.72/M
Concentrateconcentrate/llama-3.1-70b-instruct
$0.72/M$0.72/M
DeepInfraRetireddeepinfra/llama-3.1-70b-instruct
$0.40/M$0.40/M
OpenRouteropenrouter/llama-3.1-70b-instruct
$0.72/M$0.72/M

Is a provider down? AWS Bedrock status, OpenRouter status

Pricing

Averaged across 5 routes from 4 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.66 per 1M
Average output
$0.66 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.72/MBedrock, Concentrate, and OpenRouterLowest$0.40/MDeepInfra

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

7.3tokens/sacross providers

Faster than 14% of the other 599 models on the gateway

Response latency

Lower is better

1.9sacross providers

Faster than 51% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 11 published scores from 5 sources, each linked to where it was published.

10.7/ 100

Respan Index#171 of 176

176 ranked models. The shaded band is this model's 95% interval, 8.4 to 15.2. Llama 3.3 70B Instruct and GPT-4o mini fall inside it, so the gap is within the margin of error.
Llama 3.1 70B Instruct by category: Coding 0.4, Agents 6.6, Reasoning 15.7, Knowledge & language 3.5, Human preference 30.9
  1. 171Llama 3.1 70B Instruct10.7
  2. 170Llama 3.3 70B Instruct10.9
  3. 171GPT-4o mini10.7

Published scores

BenchmarkScore
HumanEvalgithub.com80.5%
WeirdMLHåvard Tveit Ihle9%

Compare Llama 3.1 70B Instruct: Llama 3.1 70B Instruct vs Llama 3.3 70B Instruct, Llama 3.1 70B Instruct vs Muse Wonder Full, Llama 3.1 70B Instruct vs Muse Wonder, Llama 3.1 70B Instruct vs Muse Ember, Llama 3.1 70B Instruct vs Muse Spark 1.3, Llama 3.1 70B Instruct vs Muse Spark 1.1

Apps

Use Llama 3.1 70B Instruct in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Llama 3.1 70B Instruct FAQ

Short answers, built from the data on this page.

Llama 3.1 70B Instruct is a model from Meta, released on Jul 23, 2024. meta-llama/Llama-3.1-70B-Instruct is a Hugging Face model based on meta-llama/Meta-Llama-3.1-70B with tags including facebook, meta, pytorch, llama.

On the Respan gateway, Llama 3.1 70B Instruct costs from $0.40 per 1M input tokens and $0.40 per 1M output tokens on DeepInfra, after gateway discounts. Averaged across its 5 routes from 4 providers, it costs $0.66 per 1M input tokens and $0.66 per 1M output tokens.

Llama 3.1 70B Instruct is available through 5 routes from 4 providers: Bedrock, Concentrate, DeepInfra, and OpenRouter.

Llama 3.1 70B Instruct accepts up to 131K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "llama-3.1-70b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Llama 3.1 70B Instruct scores 10.7 out of 100 on the Respan Index v1.1, ranking #171 of 176 models. By category: Coding 0.4, Agents 6.6, Reasoning 15.7, Knowledge & language 3.5, and Human preference 30.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Llama 3.1 70B Instruct has 11 published benchmark scores, including HumanEval 80.5%, BFCL 84.8%, and GPQA Diamond 44.2%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.