Nemotron 3.5 Lightning API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Nemotron 3.5 Lightning for your use-case.
Fastest
Fireworks (BF16)
Crusoe (BF16)
Nebius (BF16)
CoreWeave (BF16)Output speed
Total 7 providers
Lowest Latency
Fireworks (BF16)Crusoe (BF16)Nebius (BF16)CoreWeave (BF16)Time to first answer token
Total 7 providers
Lowest Price
GMI (BF16)Fireworks (BF16)Crusoe (BF16)Nebius (BF16)CoreWeave (BF16)Blended price (per 1M tokens)
Total 7 providers
Nemotron 3.5 Lightning is available through 7 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 Fireworks (BF16) (429.8 t/s), Crusoe (BF16) (300.1 t/s), and Nebius (BF16) (272.1 t/s). Speed varies significantly across providers, with a 83% difference between the fastest and slowest.
- For latency, Fireworks (BF16) (5.13s), Crusoe (BF16) (7.08s), and Nebius (BF16) (8.44s) offer the lowest time to first answer token.
- For pricing, GMI (BF16) (0.00), Fireworks (BF16) (0.04), and Crusoe (BF16) (0.05) offer the lowest blended prices per 1M tokens.
- Fireworks (BF16) offers the best performance with both the highest speed and lowest latency. For cost optimization, GMI (BF16) provides the most competitive pricing.
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: Nemotron 3.5 Lightning
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer 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
Frequently Asked Questions
Common questions about Nemotron 3.5 Lightning providers
Nemotron 3.5 Lightning is available through 7 API providers: DeepInfra (NVFP4), Nebius (BF16), CoreWeave (BF16), Bitdeer AI (BF16), GMI (BF16), Fireworks (BF16), and Crusoe (BF16). Each provider offers different performance characteristics and pricing.
Nemotron 3.5 Lightning is currently available through 7 API providers that we benchmark and track.
The fastest providers for Nemotron 3.5 Lightning by output speed are Fireworks (BF16) (429.8 t/s), Crusoe (BF16) (300.1 t/s), and Nebius (BF16) (272.1 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for Nemotron 3.5 Lightning are Fireworks (BF16) (5.13s), Crusoe (BF16) (7.08s), and Nebius (BF16) (8.44s). Lower latency means faster initial response time.
The most affordable providers for Nemotron 3.5 Lightning by blended price are GMI (BF16) ($0.00 per 1M tokens), Fireworks (BF16) ($0.04 per 1M tokens), and Crusoe (BF16) ($0.05 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 Nemotron 3.5 Lightning are GMI (BF16) ($0.00 per 1M input tokens), Fireworks (BF16) ($0.05 per 1M input tokens), and Crusoe (BF16) ($0.05 per 1M input tokens).
The providers with the lowest output token pricing for Nemotron 3.5 Lightning are GMI (BF16) ($0.00 per 1M output tokens), DeepInfra (NVFP4) ($0.20 per 1M output tokens), and Fireworks (BF16) ($0.20 per 1M output tokens).
Output speed for Nemotron 3.5 Lightning varies significantly across providers. Fireworks (BF16) is the fastest at 429.8 t/s, which is 1.8x faster than CoreWeave (BF16) at 234.5 t/s.
All 7 providers of Nemotron 3.5 Lightning support JSON mode for structured output.
6 of 7 providers support function calling for Nemotron 3.5 Lightning: DeepInfra (NVFP4), Nebius (BF16), CoreWeave (BF16), Bitdeer AI (BF16), GMI (BF16), and Fireworks (BF16).
For Nemotron 3.5 Lightning, Fireworks (BF16) offers the best performance with highest speed and lowest latency. For cost optimization, GMI (BF16) provides the most competitive pricing.
When choosing a provider for Nemotron 3.5 Lightning, 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 Nemotron 3.5 Lightning's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview