gpt-oss-20B (high): API Provider Benchmarking & Analysis
Analysis of API providers for gpt-oss-20B across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Amazon Bedrock, Groq, Together.ai, Google, Fireworks, Deepinfra, Nebius, Parasail, CompactifAI, Cloudflare, and Novita.
Comparison Summary
Output Speed (tokens/s):
Groq (1115 t/s) and 
Fireworks (353 t/s) are the fastest providers of gpt-oss-20B (high), followed by 
Google Vertex (319 t/s), 
CompactifAI (264 t/s) & 
Amazon (261 t/s).Latency (TTFT): Google Vertex (0.15s) and CompactifAI (0.19s) have the lowest latency for gpt-oss-20B (high), followed by 
Deepinfra (0.20s), Groq (0.24s) & 
Nebius Base (0.53s).Blended Price ($/M tokens): CompactifAI ($0.05) and Deepinfra ($0.07) are the most cost-effective providers for gpt-oss-20B (high), followed by Nebius Base ($0.09), Fireworks ($0.09) & 
Novita ($0.09).Input Token Price: CompactifAI ($0.03) and Deepinfra ($0.04) offer the lowest input token prices for gpt-oss-20B (high), followed by Nebius Base ($0.05), Fireworks ($0.05) & Novita ($0.05).Output Token Price: CompactifAI ($0.10) and Deepinfra ($0.16) offer the lowest output token prices for gpt-oss-20B (high), followed by Nebius Base ($0.20), Fireworks ($0.20) & Novita ($0.20).
Groq (1115 t/s) and Fireworks (353 t/s) are the fastest providers of gpt-oss-20B (high), followed by Google Vertex (319 t/s), CompactifAI (264 t/s) & Amazon (261 t/s).Latency (TTFT): Google Vertex (0.15s) and CompactifAI (0.19s) have the lowest latency for gpt-oss-20B (high), followed by Deepinfra (0.20s), Groq (0.24s) & Nebius Base (0.53s).Blended Price ($/M tokens): CompactifAI ($0.05) and Deepinfra ($0.07) are the most cost-effective providers for gpt-oss-20B (high), followed by Nebius Base ($0.09), Fireworks ($0.09) & Novita ($0.09).Input Token Price: CompactifAI ($0.03) and Deepinfra ($0.04) offer the lowest input token prices for gpt-oss-20B (high), followed by Nebius Base ($0.05), Fireworks ($0.05) & Novita ($0.05).Output Token Price: CompactifAI ($0.10) and Deepinfra ($0.16) offer the lowest output token prices for gpt-oss-20B (high), followed by Nebius Base ($0.20), Fireworks ($0.20) & Novita ($0.20).Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Together.ai