DeepInfra
About DeepInfra
DeepInfra offers cost-effective, scalable, easy-to-deploy, and production-ready machine-learning models and infrastructures for deep-learning models.
Website ↗Documentation ↗
Source ↗ · 2026-11-12T03:22:34.866718324ZService status
operational
Published API and monitored model status; excludes the website and unmonitored deployments
Official status page ↗105 indexed models
105 matching models
siliconFlow/Wan-AI/Wan2.2-T2V-A14B
Wan2.2-T2V-A14B model supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On the new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across mo
- Input modalities
- text
- Output modalities
- video
- Capabilities
- videoOutput
huggingface/ResembleAI/chatterbox
azureFoundry/azureml/runwayml-stable-diffusion-v1-5@13
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 595k step
- Input modalities
- text
- Output modalities
- image
- Capabilities
- imageOutput
vertexAI/publishers/hf-sao10k/models/l3-70b-euryale-v2.1@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 35.473%
Inference prices
- Published price : $0.70 / input_tokens_per_million · deepInfra ↗
- Published price : $0.80 / output_tokens_per_million · deepInfra ↗
vercelAIGatewayCatalog/bytedance/seedream-5.0-pro
Seedream-5.0-Pro, ByteDance's newest image generation model, delivers comprehensive upgrades for complex, lifelike image creation and editing, ushering in a new phase of controllable visual production. It stands out with precise editing control, robust commercial applicability an
- Input modalities
- text
- Output modalities
- image
azureFoundry/HuggingFace/sentence-transformers-clip-vit-b-32@1
`sentence-transformers/clip-ViT-B-32` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/sentence-transformers/clip-ViT-B-32) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request Y
- Input modalities
- text
- Output modalities
- embeddings
- Capabilities
- embeddings
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
vertexAI/publishers/hf-sentence-transformers/models/clip-vit-b-32-multilingual-v1@001
- Capabilities
- embeddings
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
sesame/csm-1b
CSM 1B is a conversational speech model from Sesame. It accepts text input and produces English speech output, with voice options spanning conversational and read-speech styles. At 1B parameters, it is suited for dialogue-oriented applications such as voice assistants and interac
- Context window
- 4,096
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput
huggingface/shibing624/text2vec-base-chinese
- Capabilities
- embeddings
Benchmarks
Inference prices
- Published price : $0.01 / input_tokens_per_million · deepInfra ↗
microsoft/wizardlm-2-8x22b
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
- Context window
- 65,535
- Input modalities
- text
- Output modalities
- text
Inference prices
- Published price : $0.48 / input_tokens_per_million · deepInfra ↗
- Published price : $0.48 / output_tokens_per_million · deepInfra ↗
xiaomiMiMo/mimo-v2.5-tts
Use built-in high-quality voices for speech synthesis
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput, streaming
xiaomiMiMo/mimo-v2.5-tts-voiceclone
Replicate any voice from audio samples
- Input modalities
- text, audio
- Output modalities
- speech
- Capabilities
- audioInput, multimodal, speechOutput, streaming
xiaomiMiMo/mimo-v2.5-tts-voicedesign
Customize voice through text description
- Input modalities
- text
- Output modalities
- speech
- Capabilities
- speechOutput, streaming
z-ai/glm-4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly enhanced capabilities in reasoning, code generation
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 12.8
- OpenCompass LLM: 16.9%
- SWE-bench: 54.2%
Inference prices
- Published price : $0.38 / input_tokens_per_million · deepInfra ↗
- Published price : $1.60 / output_tokens_per_million · deepInfra ↗
z-ai/glm-4.5-air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter size. GLM-4.5-Air also supports hybrid inference mode
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Benchmarks
- Artificial Analysis: 11.1
Inference prices
- Published price : $0.20 / input_tokens_per_million · deepInfra ↗
- Published price : $1.10 / output_tokens_per_million · deepInfra ↗