cheaperInference/deepseek-v3.1
- Context window
- 128,000
- Maximum output
- 128,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 13.7
- OpenRouter Benchmarks: 72.941%
Inference prices
- Input tokens (per 1M) : $0.27 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $1.00 / output_tokens_per_million · siliconFlow ↗
siliconFlow/fishaudio/fish-speech-1.5
Fish Speech V1.5 is a leading open-source text-to-speech (TTS) model. The model employs an innovative DualAR architecture, featuring a dual autoregressive transformer design. It supports multiple languages, with over 300,000 hours of training data for both English and Chinese, an
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
Inference prices
siliconFlow/FunAudioLLM/CosyVoice2-0.5B
CosyVoice 2 is a streaming speech synthesis model based on a large language model, employing a unified streaming/non-streaming framework design. The model enhances the utilization of the speech token codebook through finite scalar quantization (FSQ), simplifies the text-to-speech
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
Inference prices
huggingface/google/gemma-4-12B-it
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Open ASR Leaderboard: 4.18%
Inference prices
- Input tokens (per 1M) : $0.10 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $0.30 / output_tokens_per_million · siliconFlow ↗
siliconFlow/inclusionAI/Ling-1T
Ling-1T is the first flagship non-thinking model in the Ling 2.0 series, featuring 1 trillion total parameters with ≈ 50 billion active parameters per token. Built on the Ling 2.0 architecture, Ling-1T is designed to push the limits of efficient reasoning and scalable cognition.
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
siliconFlow/inclusionAI/Ling-flash-2.0
Ling-flash-2.0 is a language model from inclusionAI with a total of 100 billion parameters, of which 6.1 billion are activated per token (4.8 billion non-embedding). As part of the Ling 2.0 architecture series, it is designed as a lightweight yet powerful Mixture-of-Experts (MoE)
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Inference prices
- Input tokens (per 1M) : $0.14 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $0.57 / output_tokens_per_million · siliconFlow ↗
siliconFlow/inclusionAI/Ling-mini-2.0
Ling-mini-2.0 is a small yet high-performance large language model built on the MoE architecture. It has 16B total parameters, but only 1.4B are activated per token (non-embedding 789M), enabling extremely fast generation. Thanks to the efficient MoE design and large-scale high-q
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
siliconFlow/inclusionAI/Ring-1T
Ring-1T is an open-source, trillion-parameter thinking model released by the Bailing team. Built upon the Ling 2.0 architecture and the Ling-1T-base foundation model, it features 1 trillion total parameters with 50 billion activated parameters and supports a context window of up
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
siliconFlow/inclusionAI/Ring-flash-2.0
Ring-flash-2.0 is a high-performance thinking model, deeply optimized based on Ling-flash-2.0-base. It is a Mixture-of-Experts (MoE) model with a total of 100B parameters, but only 6.1B are activated per inference. The model leverages the independently developed 'icepop' algorith
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
siliconFlow/IndexTeam/IndexTTS-2
IndexTTS2 is a breakthrough auto-regressive zero-shot Text-to-Speech (TTS) model designed to address the challenge of precise duration control in large-scale TTS systems, which is a significant limitation in applications like video dubbing. It introduces a novel, general method f
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
Inference prices
siliconFlow/meituan-longcat/LongCat-2.0
LongCat-2.0 is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in code generation, automated workflows, and complex instruction execution. Compatible with Claude Code, OpenClaw, and ot
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Inference prices
- Cached input tokens (per 1M) : $0.02 / cache_read_tokens_per_million · siliconFlow ↗
- Input tokens (per 1M) : $0.75 / input_tokens_per_million · siliconFlow ↗
- Output tokens (per 1M) : $2.95 / output_tokens_per_million · siliconFlow ↗
siliconFlow/MiniMaxAI/MiniMax-M1-80k
MiniMax-M1 is a open-weight, large-scale hybrid-attention reasoning model with 456 B parameters and 45.9 B activated per token. It natively supports 1 M-token context, lightning attention enabling 75% FLOPs savings vs DeepSeek R1 at 100 K tokens, and leverages a MoE architecture.
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
minimax/minimax-m2
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
- Context window
- 204,800
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 18.6
- OpenCompass LLM: 74%
minimax/minimax-m2.1
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
- Context window
- 204,800
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 20.9
minimax/minimax-m2.5-20260211
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and op
- Context window
- 198,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 22.8
- OpenCompass LLM: 84.6%
- OpenRouter Benchmarks: 83.333%
siliconFlow/moonshotai/Kimi-Dev-72B
Kimi-Dev-72B is a new open-source coding large language model achieving 60.4% on SWE-bench Verified, setting a state-of-the-art result among open-source models. Optimized through large-scale reinforcement learning, it autonomously patches real codebases in Docker and earns reward
- Maximum output
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
moonshotai/kimi-k2
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis.
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 12.7
- HELM Capabilities: 86.187%
- LLM Stats · GitHub archive: 0.974
- OpenCompass LLM: 88.5%
- SWE-bench: 65.4%
moonshotai/kimi-k2-0905
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up t
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 15.3