LLMRates.ai
SiliconFlow logo

SiliconFlow API pricing

Model Aggregator

Compare the published API prices listed for SiliconFlow. Open a model for its available pricing tiers, source and conditions, or use the cost planner to estimate your own workload.

Models
62
Prompt Caching
✓
Batch Discount
—
Tool Calling
✓
Visit Website →View Official Pricing →
Model62
BAAI/bge-large-en-v1.5BGEFree—
BAAI/bge-large-zh-v1.5BGEFree—
BAAI/bge-m3BGEFree—
BAAI/bge-reranker-v2-m3BGEFree—
baidu/ERNIE-Image-TurboERNIE$0.0165/image—
ByteDance-Seed/Seed-OSS-36B-Instruct$0.2243$0.5982
deepseek-ai/DeepSeek-V3.1-TerminusDeepSeek$0.5982$1.79
deepseek-ai/DeepSeek-V3.2DeepSeek$0.5982$0.8974
deepseek-ai/DeepSeek-V4-FlashDeepSeek
$0.1496
费用发生时段: 0点～2点/8点～24点$0.4487
费用发生时段: 2点～8点$0.2243
$0.2991
$1.35
$0.673
deepseek-ai/DeepSeek-V4-ProDeepSeek$1.79$3.59
deepseek-ai/DeepSeek-V4.1-FlashDeepSeek
费用发生时段: 0点～2点/8点～24点$0.2991
费用发生时段: 2点～8点$0.1496
$1.2
$0.5982
fnlp/MOSS-TTSD-v0.5$0.007478/1M chars—
FunAudioLLM/CosyVoice2-0.5B$0.007478/1M chars—
FunAudioLLM/SenseVoiceSmallFree—
inclusionAI/Ling-flash-2.0Ling$0.1496$0.5982
inclusionAI/Ling-mini-2.0Ling$0.0748$0.2991
Kwai-Kolors/KolorsKolorsFree/image—
meituan-longcat/LongCat-2.0$0.7478$2.99
MiniMaxAI/MiniMax-M2.5MiniMax$0.3141$1.26
moonshotai/Kimi-K2.5Kimi$0.5982$3.14
moonshotai/Kimi-K2.6Kimi$0.9722$4.04
moonshotai/Kimi-K2.7-CodeKimi$0.9722$4.04
netease-youdao/bce-embedding-base_v1BCEFree—
netease-youdao/bce-reranker-base_v1BCEFree—
nex-agi/Nex-N2-Pro$0.2617$1.05
PaddlePaddle/PaddleOCR-VL-1.5FreeFree
Qwen/Qwen-ImageQwen$0.0449/image—
Qwen/Qwen-Image-EditQwen$0.0449/image—
Qwen/Qwen-Image-Edit-2509Qwen$0.0449/image—
Qwen/Qwen3-ASR-1.7BQwenFree—
Qwen/Qwen3.5-122B-A10BQwen
1314$0.2991
≤128K$0.1196
≤128K$0.1196
>128K$0.2991
128K–256K$0.2991
$2.39
$0.9572
$0.9572
$2.39
$2.39
Qwen/Qwen3.5-27BQwen
1314$0.2692
≤128K$0.0897
≤128K$0.0897
>128K$0.2692
128K–256K$0.2692
$2.15
$0.7179
$0.7179
$2.15
$2.15
Qwen/Qwen3.5-35B-A3BQwen
1314$0.2393
≤128K$0.0598
≤128K$0.0598
>128K$0.2393
128K–256K$0.2393
$1.91
$0.4786
$0.4786
$1.91
$1.91
Qwen/Qwen3.5-397B-A17BQwen
$0.0897
≤128K$0.1795
>128K$0.4487
$0.5384
$1.08
$2.69
Qwen/Qwen3.6-27BQwen$0.4487$2.69
Qwen/Qwen3.6-35B-A3BQwen$0.2692$1.62
Qwen/Qwen3.8-27BQwen$0.4487$1.79
stepfun-ai/Step-3.5-FlashStep$0.1047$0.3141
TeleAI/TeleSpeechASRFree—
tencent/Hunyuan-A13B-InstructHunyuan
$0.1496
费用发生时段: 0点～9点/18点～24点$0.1196
费用发生时段: 0点～9点/18点～24点 费用发生时段: 0点～9点/18点～24点$0.1196
费用发生时段: 9点～18点$0.1496
$0.5982
$0.4786
$0.4786
$0.5982
tencent/Hunyuan-MT-7BHunyuanFreeFree
tencent/Hy4-preview$0.8974$2.69
THUDM/GLM-4-32B-0414GLM$0.2827$0.2827
THUDM/GLM-4-9B-0414GLMFreeFree
THUDM/GLM-Z1-9B-0414GLMFreeFree
Tongyi-MAI/Z-ImageYi$0.0449/image—
Tongyi-MAI/Z-Image-TurboYi$0.015/image—
Wan-AI/Wan2.2-I2V-A14BWan——
Wan-AI/Wan2.2-T2V-A14BWan——
XingChenAGI/Xing4.0-29BFreeFree
Showing 1–50 of 62

SiliconFlow API cost examples

1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.

Standard text token prices and estimated workload cost in USD
ModelInput / 1M tokensOutput / 1M tokensEstimated costPricing conditions
PaddlePaddle/PaddleOCR-VL-1.5SiliconFlowFreeFreeFreeRegion not specifiedView official pricing
tencent/Hunyuan-MT-7BSiliconFlowFreeFreeFreeRegion not specifiedView official pricing
XingChenAGI/Xing4.0-29BSiliconFlowFreeFreeFreeRegion not specifiedView official pricing
inclusionAI/Ling-mini-2.0SiliconFlow$0.0748$0.2991$0.1346Region not specifiedView official pricing
Qwen/Qwen3.5-35B-A3BSiliconFlow$0.0598$0.4786$0.1555Region not specifiedInput tier up to 128K tokens per requestView official pricing
stepfun-ai/Step-3.5-FlashSiliconFlow$0.1047$0.3141$0.1675Region not specifiedView official pricing

Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.

Calculate costs for your workload →