This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Meta has launched a newer release, Llama 3.3 Instruct 70B. We suggest considering it instead.
Llama 3.1 Instruct 70B API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Llama 3.1 Instruct 70B for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
4 endpoints from 2 providers
Lowest Cost per Task
Cost per Intelligence Index task
4 endpoints from 2 providers
Llama 3.1 70B is available through 4 API endpoints from 2 providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
Pricing
Cost per Intelligence Index Task: Llama 3.1 Instruct 70B
Pricing: Cache Hit, Input, and Output: Llama 3.1 Instruct 70B
Output Speed vs. Cost per Task: Llama 3.1 Instruct 70B
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Llama 3.1 Instruct 70B
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Llama 3.1 Instruct 70B
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Llama 3.1 Instruct 70B
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Llama 3.1 Instruct 70B providers
Llama 3.1 Instruct 70B is available through 4 API endpoints from 2 providers: Amazon Standard, DeepInfra, Amazon Latency Optimized, and DeepInfra (Turbo, FP8). Each endpoint offers different performance characteristics and pricing.
Llama 3.1 Instruct 70B is currently available through 4 API endpoints from 2 providers that we benchmark and track.
The providers with the lowest time to first answer token for Llama 3.1 Instruct 70B are DeepInfra (Turbo, FP8) (7.21s) and DeepInfra (9.21s). Lower latency means faster initial response time.
The most affordable providers for Llama 3.1 Instruct 70B by blended price are DeepInfra ($0.40 per 1M tokens), DeepInfra (Turbo, FP8) ($0.40 per 1M tokens), and Amazon Standard ($0.72 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Llama 3.1 Instruct 70B are DeepInfra ($0.40 per 1M input tokens), DeepInfra (Turbo, FP8) ($0.40 per 1M input tokens), and Amazon Standard ($0.72 per 1M input tokens).
The providers with the lowest output token pricing for Llama 3.1 Instruct 70B are DeepInfra ($0.40 per 1M output tokens), DeepInfra (Turbo, FP8) ($0.40 per 1M output tokens), and Amazon Standard ($0.72 per 1M output tokens).
Prices for Llama 3.1 Instruct 70B vary up to 2.3x across providers. The most affordable is DeepInfra at $0.40 per 1M tokens, while Amazon Latency Optimized charges $0.90 per 1M tokens.
2 of 4 endpoints support JSON mode for Llama 3.1 Instruct 70B: DeepInfra and DeepInfra (Turbo, FP8).
All 4 endpoints of Llama 3.1 Instruct 70B support function calling (tool use).
When choosing a provider for Llama 3.1 Instruct 70B, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Llama 3.1 Instruct 70B's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview