Average response time
24.21 s
Estimated 500-token answer. Across 35 models with recent complete speed data.
Average response start
1.84 s
Wait until the first token. Across 35 models with recent response start data.
Average output speed
33.4 tok/s
Generated tokens per second. Across 35 models with recent output speed data.
AI Models available from SiliconFlow Prices and recent speed measurements below are for SiliconFlow endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
No models match these filters.
Model ZA Current pricing & context
Input price $1.3 / 1M tokens
Context 1M Speed measurements
500-token response 26.91 s
Response starts 6.08 s
Output speed 24.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $0.8592 / 1M tokens
Context 262.1K Speed measurements
500-token response 13.77 s
Response starts 1.86 s
Output speed 42.0 tok/s Model details
Model type Text
Provider options 1 Model NA Current pricing & context
Input price $0.5 / 1M tokens
Context 262.1K Speed measurements
500-token response 4.81 s
Response starts 0.87 s
Output speed 127.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.2 / 1M tokens
Context 262.1K Speed measurements
500-token response 12.15 s
Response starts 1.52 s
Output speed 47.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.3 / 1M tokens
Context 262.1K Speed measurements
500-token response 23.41 s
Response starts 1.67 s
Output speed 23.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $1.5 / 1M tokens
Context 1M Speed measurements
500-token response 19.61 s
Response starts 1.09 s
Output speed 27.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.13 / 1M tokens
Context 1M Speed measurements
500-token response 11.33 s
Response starts 1.72 s
Output speed 52.0 tok/s Model details
Model type Text
Provider options 1 Model T Current pricing & context
Input price $0.066 / 1M tokens
Context 262.1K Speed measurements
500-token response 6.94 s
Response starts 1.73 s
Output speed 96.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $0.77 / 1M tokens
Context 262.1K Speed measurements
500-token response 15.28 s
Response starts 1.76 s
Output speed 37.0 tok/s Model details
Model type Text
Provider options 1 Model ZA Current pricing & context
Input price $1.19 / 1M tokens
Context 204.8K Speed measurements
500-token response 14.81 s
Response starts 1.99 s
Output speed 39.0 tok/s Model details
Model type Text
Provider options 1 Model G Current pricing & context
Input price $0.12 / 1M tokens
Context 262.1K Speed measurements
500-token response 18.55 s
Response starts 1.31 s
Output speed 29.0 tok/s Model details
Model type Text
Provider options 1 Model G Current pricing & context
Input price $0.13 / 1M tokens
Context 262.1K Speed measurements
500-token response 85.16 s
Response starts 1.83 s
Output speed 6.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.1 / 1M tokens
Context 262.1K Speed measurements
500-token response 46.88 s
Response starts 1.43 s
Output speed 11.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.24 / 1M tokens
Context 262.1K Speed measurements
500-token response 33.18 s
Response starts 3.76 s
Output speed 17.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.25 / 1M tokens
Context 262.1K Speed measurements
500-token response 29.12 s
Response starts 2.81 s
Output speed 19.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.26 / 1M tokens
Context 262.1K Speed measurements
500-token response 20.49 s
Response starts 1.26 s
Output speed 26.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $0.3 / 1M tokens
Context 204.8K Speed measurements
500-token response 11.74 s
Response starts 1.10 s
Output speed 47.0 tok/s Model details
Model type Text
Provider options 1 Model ZA Current pricing & context
Input price $0.95 / 1M tokens
Context 204.8K Speed measurements
500-token response 13.59 s
Response starts 1.97 s
Output speed 43.0 tok/s Model details
Model type Text
Provider options 1 Model S Current pricing & context
Input price $0.1 / 1M tokens
Context 262.1K Speed measurements
500-token response 10.97 s
Response starts 1.17 s
Output speed 51.0 tok/s Model details
Model type Text
Provider options 1 Model M Current pricing & context
Input price $0.45 / 1M tokens
Context 262.1K Speed measurements
500-token response 14.05 s
Response starts 1.55 s
Output speed 40.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.259 / 1M tokens
Context 163.8K Speed measurements
500-token response 21.61 s
Response starts 1.61 s
Output speed 25.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.04 / 1M tokens
Context 32.8K Speed measurements
500-token response N/a
Response starts N/a
Output speed N/a Model details
Model type Embeddings
Provider options 1 Model Q Current pricing & context
Input price $0.29 / 1M tokens
Context 262.1K Speed measurements
500-token response 8.13 s
Response starts 1.28 s
Output speed 73.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.29 / 1M tokens
Context 262.1K Speed measurements
500-token response 52.41 s
Response starts 2.41 s
Output speed 10.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.27 / 1M tokens
Context 163.8K Speed measurements
500-token response 20.95 s
Response starts 1.72 s
Output speed 26.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.27 / 1M tokens
Context 163.8K Speed measurements
500-token response 31.22 s
Response starts 1.80 s
Output speed 17.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.27 / 1M tokens
Context 163.8K Speed measurements
500-token response 29.77 s
Response starts 1.99 s
Output speed 18.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $0.05 / 1M tokens
Context 131.1K Speed measurements
500-token response 23.10 s
Response starts 1.36 s
Output speed 23.0 tok/s Model details
Model type Text
Provider options 1 Model O Current pricing & context
Input price $0.04 / 1M tokens
Context 131.1K Speed measurements
500-token response 46.80 s
Response starts 1.35 s
Output speed 11.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.07 / 1M tokens
Context 262.1K Speed measurements
500-token response 14.29 s
Response starts 2.09 s
Output speed 41.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.09 / 1M tokens
Context 262.1K Speed measurements
500-token response 31.72 s
Response starts 2.31 s
Output speed 17.0 tok/s Model details
Model type Text
Provider options 1 Model ZA Current pricing & context
Input price $0.14 / 1M tokens
Context 131.1K Speed measurements
500-token response 17.97 s
Response starts 1.84 s
Output speed 31.0 tok/s Model details
Model type Text
Provider options 1 Model T Current pricing & context
Input price $0.14 / 1M tokens
Context 131.1K Speed measurements
500-token response 30.54 s
Response starts 1.13 s
Output speed 17.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.5 / 1M tokens
Context 163.8K Speed measurements
500-token response 25.62 s
Response starts 1.81 s
Output speed 21.0 tok/s Model details
Model type Text
Provider options 1 Model Q Current pricing & context
Input price $0.14 / 1M tokens
Context 131.1K Speed measurements
500-token response 31.14 s
Response starts 1.73 s
Output speed 17.0 tok/s Model details
Model type Text
Provider options 1 Model D Current pricing & context
Input price $0.25 / 1M tokens
Context 163.8K Speed measurements
500-token response 29.16 s
Response starts 1.38 s
Output speed 18.0 tok/s Model details
Model type Text
Provider options 1 Model data fetched Jul 15, 2026, 10:17 PM UTC .
Practical comparison guide
How to evaluate SiliconFlow as an AI inference provider SiliconFlow currently has 36 indexed models on this site, including 35 text, 1 embeddings. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare SiliconFlow with alternative hosts on each model page.
Review model coverage SiliconFlow offers model-specific routes rather than one interchangeable service. Check modality, context window, supported inputs, and parameter support before comparing price. The largest published context window in this catalog is 1M tokens.
Interpret price and speed together The lowest published input price shown here is $0.04 / 1M tokens. Recent 500-token response measurements are available for 35 models; missing measurements remain visible and are never estimated.
Confirm deployment requirements SiliconFlow lists its headquarters as SG. Published datacenter coverage: US. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.
Compare LLM providers → Browse all AI models → Understand speed and pricing data → 
