Inference provider
SiliconFlow API pricing: every model, compared
We track 47 SiliconFlow prices that other providers also sell. SiliconFlow has the lowest listed price for 19 of them; for the rest, the table shows how much more you pay than at the cheapest provider.
Standard list prices in USD. Last price change Oct 28, 2026. SiliconFlow's official pricing page. How we rank.
LLMs, most widely offered first
SiliconFlow LLM prices vs the cheapest provider
| Model | Rank | Cheapest elsewhere | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|---|
| gpt-oss-120b | #4 of 18 | W&B Inference (CoreWeave)you pay 131% more here | $0.05 | $0.45 | 131K |
| GLM-5.2 | #3 of 13 | DeepInfrayou pay 72% more here | $1.30 | $4.09 | 1M |
| GLM-5.3 | #4 of 12 | DeepInfrayou pay 28% more here | $1.40 | $4.40 | 1M |
| GLM-5.3-Flash | #1 of 11 | SiliconFlow is cheapest | $0.15 | $0.50 | 1M |
| DeepSeek V4 Flash 0731 | #5 of 10 | DeepInfrayou pay 214% more here | $0.22 | $0.66 | 1M |
| gpt-oss-20b | #4 of 10 | W&B Inference (CoreWeave)you pay 36% more here | $0.04 | $0.18 | 131K |
| Kimi K3 | #1 of 9 | SiliconFlow is cheapest | $2.70 | $13.50 | 1M |
| DeepSeek V4 Pro 0813 | #3 of 8 | DeepInfrayou pay 22% more here | $1.32 | $3.96 | 1M |
| DeepSeek-R1 | #1 of 8 | SiliconFlow is cheapest | $0.50 | $2.18 | 164K |
| DeepSeek-V3 | #1 of 8 | SiliconFlow is cheapest | $0.25 | $1.00 | 164K |
| DeepSeek-V3.2 | #3 of 8 | DeepInfrayou pay 6% more here | $0.27 | $0.42 | 164K |
| Kimi K2.6 | #2 of 8 | W&B Inference (CoreWeave)you pay 7% more here | $0.77 | $3.40 | 262K |
| Kimi K2.7 Code | #3 of 8 | DeepInfrayou pay 17% more here | $0.8592 | $3.80 | 262K |
| DeepSeek-V3.1 | #2 of 7 | DeepInfrayou pay 6% more here | $0.27 | $1.00 | 164K |
| DeepSeek-V4-Flash | #2 of 7 | DeepInfrayou pay 49% more here | $0.13 | $0.28 | 1M |
| Gemma 4 26B A4B IT | #5 of 7 | DeepInfrayou pay 49% more here | $0.14 | $0.40 | 262K |
| GLM-5.1 | #2 of 7 | DeepInfrayou pay 10% more here | $1.19 | $3.74 | 205K |
| Kimi K2.5 | #1 of 7 | SiliconFlow is cheapest | $0.45 | $2.25 | 262K |
| MiniMax-M3 | #3 of 7 | W&B Inference (CoreWeave)you pay 27% more here | $0.30 | $1.20 | 1M |
| Qwen3 32B | #4 of 7 | DeepInfrayou pay 90% more here | $0.14 | $0.57 | 131K |
| DeepSeek V4 Pro | #2 of 6 | DeepInfrayou pay 18% more here | $1.50 | $3.14 | 1M |
| Gemma 4 31B IT | #6 of 6 | W&B Inference (CoreWeave)you pay 408% more here | $0.75 | $1.00 | 262K |
| Qwen2.5-72B-Instruct | #4 of 6 | Nebius Token Factoryyou pay 199% more here | $0.59 | $0.59 | 33K |
| Qwen3.6 35B-A3B | #5 of 6 | DeepInfrayou pay 102% more here | $0.24 | $1.80 | 262K |
| GLM-5 | #2 of 5 | DeepInfrayou pay 39% more here | $0.95 | $2.55 | 205K |
| Qwen3.8 2.4T A95B | #1 of 5 | SiliconFlow is cheapest | $2.00 | $6.00 | 1M |
| DeepSeek V4 Flash Vision Exp | #2 of 4 | DeepSeekyou pay 26% more here | $0.44 | $1.32 | 1M |
| DeepSeek-V3.1-Terminus | #1 of 4 | SiliconFlow is cheapest | $0.27 | $1.00 | 164K |
| GLM-4.5-Air | #2 of 4 | Novita AIyou pay 3% more here | $0.14 | $0.86 | 131K |
| Qwen2.5-7B-Instruct | #1 of 4 | SiliconFlow is cheapest | $0.05 | $0.05 | 33K |
| Qwen3 VL 30B A3B Instruct | #4 of 4 | DeepInfrayou pay 78% more here | $0.29 | $1.00 | 262K |
| Qwen3-14B | #2 of 4 | Nebius Token Factoryyou pay 2% more here | $0.07 | $0.28 | 131K |
| Qwen3-Coder-480B-A35B-Instruct | #1 of 4 | SiliconFlow is cheapest | $0.25 | $1.00 | 262K |
| Qwen3.5 122B-A10B | #1 of 4 | SiliconFlow is cheapest | $0.26 | $2.08 | 262K |
| Qwen3.5 27B | #1 of 4 | SiliconFlow is cheapest | $0.25 | $2.00 | 262K |
| Qwen3.5 35B-A3B | #2 of 4 | DeepInfrayou pay 77% more here | $0.24 | $1.80 | 262K |
| Qwen3.6 27B | #1 of 4 | SiliconFlow is cheapest | $0.30 | $3.20 | 262K |
| GLM-5V-Turbo | #1 of 3 | SiliconFlow is cheapest | $1.20 | $4.00 | 200K |
| Hy3 | #1 of 3 | SiliconFlow is cheapest | $0.132 | $0.528 | 262K |
| Qwen3-30B-A3B-Instruct-2507 | #1 of 3 | SiliconFlow is cheapest | $0.09 | $0.30 | 262K |
| Qwen3-Coder-30B-A3B-Instruct | #2 of 3 | Novita AIyou pay 2% more here | $0.07 | $0.28 | 262K |
| Qwen3-VL-30B-A3B-Thinking | #3 of 3 | Fireworks AIyou pay 78% more here | $0.29 | $1.00 | 262K |
| Qwen3-VL-8B-Instruct | #3 of 3 | Novita AIyou pay 65% more here | $0.18 | $0.68 | 262K |
| Qwen3.5 9B | #1 of 3 | SiliconFlow is cheapest | $0.10 | $0.15 | 262K |
| DeepSeek-V3.2-Exp | #1 of 2 | SiliconFlow is cheapest | $0.27 | $0.41 | 164K |
| Qwen3-8B | #1 of 2 | SiliconFlow is cheapest | $0.06 | $0.06 | 131K |
| Qwen3-VL-32B-Instruct | #1 of 2 | SiliconFlow is cheapest | $0.20 | $0.60 | 262K |
Rank and difference use the blended price (3 input : 1 output tokens). Equal prices share a rank.
Ranked for your volume
gpt-oss-120b monthly cost by provider
Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.
More requirements: caching, context, features, provider
| Provider | Estimated / month | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
1 W&B Inference (CoreWeave)lowest for your volumePricing page | $0.64 | $0.03 | $0.17 | Not listed | 131,000 |
2 DeepInfraPricing page | $0.71 | $0.037 | $0.17 | Not listed | 131,072 |
3 Novita AIPricing page | $1.00 | $0.05 | $0.25 | Not listed | 131,072 |
4 SiliconFlowPricing page | $1.40 | $0.05 | $0.45 | Not listed | 131,000 |
5 OVHcloud AI EndpointsBilled in EUR: €0.08 input, €0.40 output per 1M tokens. USD at the ECB rate of Oct 30, 2026 (1.1172).Pricing page | $1.79 | $0.0894 | $0.4469 | Not listed | 131,000 |
6 BasetenPricing page | $2.00 | $0.10 | $0.50 | $0.10 | 128,072 |
7 Amazon BedrockPricing page | $2.70 | $0.15 | $0.60 | Not listed | 128,000 |
8 Fireworks AIPricing page | $2.70 | $0.15 | $0.60 | $0.015 | 131,072 |
9 Microsoft Azure AI FoundryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
10 Nebius Token FactoryPricing page | $2.70 | $0.15 | $0.60 | Not listed | 131,072 |
Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.
Ranked #1? Show it on your site
SiliconFlow has the lowest blended list price (3 input : 1 output tokens) for these models. The badge states that basis, updates daily and always shows the current rank, whatever it is; ranking is by price only.
<a href="https://aiselect.online/models/glm-5-3-flash"><img src="https://aiselect.online/badge/glm-5-3-flash/siliconflow.svg" alt="GLM-5.3-Flash API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/kimi-k3"><img src="https://aiselect.online/badge/kimi-k3/siliconflow.svg" alt="Kimi K3 API price ranking on AISelect" height="20"></a>
<a href="https://aiselect.online/models/deepseek-r1"><img src="https://aiselect.online/badge/deepseek-r1/siliconflow.svg" alt="DeepSeek-R1 API price ranking on AISelect" height="20"></a>Compare more
Other providers
Alibaba Cloud Model Studio, Amazon Bedrock, Anthropic, Baseten, Cloudflare Workers AI, Cohere, DeepInfra, DeepSeek, fal, Fireworks AI, FriendliAI, Google Cloud Vertex AI, Google Gemini API, IBM watsonx.ai, Lambda, Microsoft Azure AI Foundry, Mistral AI, Moonshot AI, Nebius Token Factory, Novita AI, Nscale, OpenAI, Oracle Cloud Generative AI, OVHcloud AI Endpoints, Perplexity, Replicate, SambaNova, Scaleway, Together AI, W&B Inference (CoreWeave), xAI, Z.ai