Llama 3.3 Instruct 70B API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Llama 3.3 Instruct 70B for your use-case.
Fastest
Groq
Google Vertex
Amazon
Azure
ScalewayOutput speed
Total 13 providers
Lowest Latency
Google VertexGroq
CoreWeaveAmazonScalewayTime to first token
Total 13 providers
Lowest Price
DeepInfra (Turbo, FP8)
Novita
Parasail (FP8)
CloudflareGroqBlended price (per 1M tokens)
Total 13 providers
Llama 3.3 70B is available through 13 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Groq (270.4 t/s), Google Vertex (150.7 t/s), and Amazon (121.4 t/s). Speed varies significantly across providers, with a 1467% difference between the fastest and slowest.
- For latency, Google Vertex (0.64s), Groq (0.85s), and CoreWeave (0.92s) offer the lowest time to first token.
- For pricing, DeepInfra (Turbo, FP8) (0.12), Novita (0.16), and Parasail (FP8) (0.17) offer the lowest blended prices per 1M tokens. Prices vary up to 8.6x across providers.
Highlights
Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Llama 3.3 Instruct 70B
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
 Fireworks | 131k | Open | -- | -- | -- | -- | -- | ||
| Google | 128k | Open | -- | 151 | 0.64 | 3.96 | -- | ||
| Groq | 131k | Open | -- | 270 | 0.85 | 2.70 | -- | ||
| Novita | 131k | Open | -- | 43 | 1.75 | 13.40 | -- | ||
| Parasail | 131k | Open | -- | 69 | 2.71 | 9.92 | -- | ||
 SambaNova | 128k | Open | -- | -- | -- | -- | -- | ||
| CoreWeave | 128k | Open | -- | 81 | 0.92 | 7.11 | -- | ||
 Together AI | 131k | Open | -- | 69 | 1.60 | 8.82 | -- | ||
| Microsoft Azure | 128k | Open | -- | 112 | 2.31 | 6.78 | -- | ||
| DeepInfra | 131k | Open | -- | 18 | 2.37 | 30.52 | -- | ||
| Cloudflare | 24k | Open | -- | -- | -- | -- | -- | ||
| Amazon Bedrock | 128k | Open | -- | 126 | 1.13 | 5.09 | -- | ||
| Scaleway | 100k | Open | -- | 83 | 1.36 | 7.37 | -- | ||
Frequently Asked Questions
Common questions about Llama 3.3 Instruct 70B providers
Llama 3.3 Instruct 70B is available through 13 API providers: Fireworks, Google Vertex, Groq, Novita, Parasail (FP8), SambaNova, CoreWeave, Together AI Turbo, Azure, DeepInfra (Turbo, FP8), Cloudflare, Amazon, and Scaleway. Each provider offers different performance characteristics and pricing.
Llama 3.3 Instruct 70B is currently available through 13 API providers that we benchmark and track.
The fastest providers for Llama 3.3 Instruct 70B by output speed are Groq (270.4 t/s), Google Vertex (150.7 t/s), and Amazon (121.4 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first token for Llama 3.3 Instruct 70B are Google Vertex (0.64s), Groq (0.85s), and CoreWeave (0.92s). Lower latency means faster initial response time.
The most affordable providers for Llama 3.3 Instruct 70B by blended price are DeepInfra (Turbo, FP8) ($0.12 per 1M tokens), Novita ($0.16 per 1M tokens), and Parasail (FP8) ($0.17 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 3.3 Instruct 70B are DeepInfra (Turbo, FP8) ($0.10 per 1M input tokens), Novita ($0.14 per 1M input tokens), and Parasail (FP8) ($0.22 per 1M input tokens).
The providers with the lowest output token pricing for Llama 3.3 Instruct 70B are DeepInfra (Turbo, FP8) ($0.32 per 1M output tokens), Novita ($0.40 per 1M output tokens), and Parasail (FP8) ($0.50 per 1M output tokens).
Prices for Llama 3.3 Instruct 70B vary up to 8.6x across providers. The most affordable is DeepInfra (Turbo, FP8) at $0.12 per 1M tokens, while Scaleway charges $1.05 per 1M tokens.
Output speed for Llama 3.3 Instruct 70B varies significantly across providers. Groq is the fastest at 270.4 t/s, which is 15.7x faster than DeepInfra (Turbo, FP8) at 17.3 t/s.
12 of 13 providers support JSON mode for Llama 3.3 Instruct 70B: Fireworks, Google Vertex, Groq, Novita, Parasail (FP8), SambaNova, CoreWeave, Together AI Turbo, Azure, DeepInfra (Turbo, FP8), Cloudflare, and Scaleway.
All 13 providers of Llama 3.3 Instruct 70B support function calling (tool use).
The best provider for Llama 3.3 Instruct 70B depends on your priorities: Groq offers the highest output speed, Google Vertex has the lowest latency, and DeepInfra (Turbo, FP8) provides the most competitive pricing.
When choosing a provider for Llama 3.3 Instruct 70B, consider: output speed (for throughput-intensive tasks), 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 3.3 Instruct 70B's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview