API Status

fireworks Provider Benchmarks

Comprehensive performance summary covering 6 models.

This provider hub highlights throughput and latency trends across every fireworks model monitored by LLM Benchmarks. Use it to compare hosting tiers, track regressions, and discover the fastest variants in the catalogue.

Visit fireworks Official Website

Provider Snapshot

Models Tracked

6

Avg Tokens / Second

54.80

Avg Time to First Token (ms)

0.00

Last Updated

Jun 25, 2026

Key Takeaways

  • 6 fireworks models are actively benchmarked with 1445 total measurements across 1334 benchmark runs.

  • GPT-oss-120b leads the fleet with 116.00 tokens/second, while glm-5p1 delivers 29.30 tok/s.

  • Performance varies by 295.9% across the fireworks model lineup, indicating diverse optimization strategies for different use cases.

  • The fireworks model fleet shows varied performance characteristics (54.9% variation coefficient), reflecting diverse model architectures.

Fastest Models

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
fireworksGPT-oss-120b116.0033.20195.000.00
fireworksminimax-m2p767.802.64111.000.00
fireworkskimi-k2p645.502.2783.000.00
fireworkskimi-k2p536.001.1771.400.00
fireworksglm-5p234.206.16116.000.00
fireworksglm-5p129.305.9755.300.00

All Models

Complete list of all fireworks models tracked in the benchmark system. Click any model name to view detailed performance data.

ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
fireworksglm-5p129.305.9755.300.00
fireworksglm-5p234.206.16116.000.00
fireworksGPT-oss-120b116.0033.20195.000.00
fireworkskimi-k2p536.001.1771.400.00
fireworkskimi-k2p645.502.2783.000.00
fireworksminimax-m2p767.802.64111.000.00

Featured Models

Frequently Asked Questions

Based on recent tests, GPT-oss-120b shows the highest average throughput among tracked fireworks models.

This provider summary aggregates 1445 individual prompts measured across 1334 monitoring runs over the past month.