SiliconFlow

SiliconFlow Pricing

Visit siliconflow.com →

Per-token pricing for 39 open-source LLMs on SiliconFlow — a major inference platform serving Qwen, DeepSeek, GLM, Hunyuan and gpt-oss at competitive rates.

Last updated: Nov 21, 2026

Get our weekly newsletter on pricing changes, new releases, and tools.

SiliconFlow offers free models

$1 credit + free models — see the full SiliconFlow free tier guide

39
Models
$0.04
Cheapest Input/1M
$0.15
Cheapest Output/1M
7
Model Authors
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Context
Quant
Input/1M
Output/1M
131k
fp8
$0.040
$0.180
262k
fp8
$0.070
$0.280
262k
fp8
$0.090
$0.300
262k
fp8
$0.100
$0.150
1049k
fp8
$0.100
$0.400
1049k
fp8
$0.130
$0.280
262k
fp8
$0.140
$0.400
131k
fp8
$0.140
$0.570
131k
fp8
$0.140
$0.860
deepseek/deepseek-v4.1-flash-1017
1049k
fp8
$0.150
$0.600
131k
fp8
$0.150
$0.600
deepseek-ai/DeepSeek-V4-Flash-0731
1049k
fp8
$0.220
$0.660
262k
fp8
$0.240
$1.800
262k
fp8
$0.240
$1.800
164k
fp8
$0.250
$1.000
262k
fp8
$0.250
$2.000
164k
fp8
$0.259
$0.800
262k
fp8
$0.260
$2.080
164k
fp8
$0.270
$1.000
164k
fp8
$0.270
$1.000
164k
fp8
$0.270
$0.410
262k
fp8
$0.290
$1.000
1049k
fp8
$0.300
$1.200
262k
fp8
$0.300
$3.200
262k
fp8
$0.425
$2.550
1049k
fp8
$0.440
$1.320
164k
fp8
$0.500
$2.180
262k
int4
$0.500
$2.500
1049k
fp8
$0.651
$2.046
1049k
fp8
$0.700
$1.900
262k
fp8
$0.750
$1.000
262k
fp8
$0.770
$3.400
1049k
fp8
$0.834
$2.501
262k
fp8
$0.859
$3.800
1049k
fp8
$0.900
$1.700
205k
fp8
$0.950
$2.550
205k
fp8
$1.190
$3.740
deepseek/deepseek-v4-pro-0813
1049k
fp8
$1.320
$3.960
1049k
fp8
$2.000
$6.000

Pricing for SiliconFlow endpoints aggregated via OpenRouter. Prices per 1M tokens.

About SiliconFlow

SiliconFlow is a large inference platform — especially strong across APAC — that serves open-source models through an OpenAI-compatible API. Its catalog leans into the leading open Chinese models (Qwen, DeepSeek, GLM, Tencent Hunyuan) alongside gpt-oss and other open-weight releases, with competitive per-token pricing.

Many models are served at fp8 or int4 quantization for lower cost and higher throughput. The table below shows the models SiliconFlow currently serves with public per-token pricing, the quantization each price applies to, and context length.

SiliconFlow Pricing FAQ

How much does SiliconFlow cost?

SiliconFlow charges per token, with input prices for smaller open models starting around $0.04–$0.10 per million tokens. See the live table above for current per-model input and output prices.

Which models does SiliconFlow support?

A broad catalog of open-source LLMs — Qwen, DeepSeek, GLM, Tencent Hunyuan, gpt-oss and more. The table above lists the models with public per-token pricing.

What quantizations does SiliconFlow use?

Many SiliconFlow models are served at fp8 or int4 quantization to lower cost and increase throughput. The table shows the quantization each listed price applies to.

Is SiliconFlow OpenAI-compatible?

Yes. SiliconFlow exposes an OpenAI-compatible API, so switching from another provider is usually just a base-URL and API-key change.