gpt-oss-120b (low) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of gpt-oss-120b (low) for your use-case.
Fastest
Cerebras
SambaNova
Groq
Azure
Nebius BaseOutput speed
Total 17 providers
Lowest Latency
CerebrasSambaNovaGroqAzure
BasetenTime to first answer token
Total 17 providers
Lowest Price
CoreWeave
DeepInfra
Crusoe
Novita
Google VertexBlended price (per 1M tokens)
Total 17 providers
gpt-oss-120b (low) is available through 17 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 Cerebras (1,650.8 t/s), SambaNova (725.8 t/s), and Groq (469.3 t/s). Speed varies significantly across providers, with a 3467% difference between the fastest and slowest.
- For latency, Cerebras (1.70s), SambaNova (3.82s), and Groq (5.00s) offer the lowest time to first answer token.
- For pricing, CoreWeave (0.04), DeepInfra (0.05), and Crusoe (0.07) offer the lowest blended prices per 1M tokens. Prices vary up to 8.9x across providers.
- Cerebras offers the best performance with both the highest speed and lowest latency. For cost optimization, CoreWeave 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: gpt-oss-120b (low)
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
 Snowflake | 131k | Open | -- | -- | -- | -- | -- | ||
 Hyperbolic | 131k | Open | -- | -- | -- | -- | -- | ||
| Nebius | 128k | Open | -- | 233 | 1.05 | 11.76 | 8.57 | ||
| Crusoe | 131k | Open | -- | 221 | 0.36 | 11.68 | 9.05 | ||
| SambaNova | 131k | Open | -- | 726 | 1.07 | 4.51 | 2.76 | ||
| Google | 131k | Open | -- | 161 | 0.48 | 15.97 | 12.39 | ||
| DeepInfra | 131k | Open | -- | 46 | 0.80 | 54.83 | 43.22 | ||
| CoreWeave | 131k | Open | -- | 52 | 1.39 | 49.73 | 38.67 | ||
| Cerebras | 131k | Open | -- | 1,651 | 0.49 | 2.00 | 1.21 | ||
| Microsoft Azure | 131k | Open | -- | 342 | 0.81 | 8.13 | 5.85 | ||
 Cloudflare | 128k | Open | -- | -- | -- | -- | -- | ||
| Baseten | 128k | Open | -- | 233 | 0.23 | 10.97 | 8.59 | ||
 Amazon Bedrock | 131k | Open | -- | 74 | 0.93 | 34.67 | 26.99 | ||
 Parasail | 131k | Open | -- | 130 | 0.89 | 20.12 | 15.39 | ||
 Together AI | 131k | Open | -- | 70 | 0.81 | 36.53 | 28.58 | ||
| Groq | 131k | Open | -- | 469 | 0.73 | 6.06 | 4.26 | ||
| Novita | 131k | Open | -- | 71 | 0.97 | 36.27 | 28.25 | ||
Frequently Asked Questions
Common questions about gpt-oss-120b (low) providers
gpt-oss-120b (low) is available through 17 API providers: Snowflake, Hyperbolic, Nebius Base, Crusoe, SambaNova, Google Vertex, DeepInfra, CoreWeave, Cerebras, Azure, Cloudflare, Baseten, Amazon, Parasail, Together AI, Groq, and Novita. Each provider offers different performance characteristics and pricing.
gpt-oss-120b (low) is currently available through 17 API providers that we benchmark and track.
All 17 providers of gpt-oss-120b (low) support JSON mode for structured output.
16 of 17 providers support function calling for gpt-oss-120b (low): Hyperbolic, Nebius Base, Crusoe, SambaNova, Google Vertex, DeepInfra, CoreWeave, Cerebras, Azure, Cloudflare, Baseten, Amazon, Parasail, Together AI, Groq, and Novita.
When choosing a provider for gpt-oss-120b (low), 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 gpt-oss-120b (low)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview