llms.txt
Compare with other sites' llms.txt files →# Infer
> Infer is a unified inference API for image, video, audio, and chat models. One API key, one bill, pay only for what you run.
## Models
- [Seedance 2.5](https://tryinfer.com/models/seedance-2.5): Text to video, $0.231 per second
- [Seedance 2.0](https://tryinfer.com/models/seedance-2.0): Image to video, $0.13 per second
- [Happyhorse 1.0](https://tryinfer.com/models/happyhorse-1.0): Text to video, $0.11 per second
- [Nano Banana 2](https://tryinfer.com/models/nano-banana-2): Text to image, $0.039 per image
- [GPT Image 2](https://tryinfer.com/models/gpt-image-2): Text to image, $0.05 per image
- [Flux 2](https://tryinfer.com/models/flux-2): Text to image, $0.02 per image
- [Nano Banana](https://tryinfer.com/models/nano-banana): Text to image, $0.039 per image
- [Ideogram 4](https://tryinfer.com/models/ideogram-4): Text to image, $0.02 per image
- [Uni 1](https://tryinfer.com/models/uni-1): Text to image, $0.04 per image
- [Qwen Image Max Preview](https://tryinfer.com/models/qwen-image-max-preview): Text to image, $0.025 per image
- [Wan 2.7](https://tryinfer.com/models/wan2.7): Text to image, $0.04 per image
- [Seedream 4](https://tryinfer.com/models/seedream-4): Text to image, $0.03 per image
- [Seedream 4.5](https://tryinfer.com/models/seedream-4.5): Text to image, $0.03 per image
- [SAM 3](https://tryinfer.com/models/sam3): Detection, $0.01 per image
- [Kling V3](https://tryinfer.com/models/kling-v3): Image to video, $0.07 per second
- [Veo 3.1](https://tryinfer.com/models/veo-3.1): Image to video, $0.09 per second
- [Happyhorse 1.1](https://tryinfer.com/models/happyhorse-1.1): Image to video, $0.11 per second
- [Wan 2.2](https://tryinfer.com/models/wan2.2): Image to video, $0.04 per second
- [LTX 2.3](https://tryinfer.com/models/ltx-2-3): Image to video, $0.07 per second
- [Eleven v3](https://tryinfer.com/models/eleven-v3): Text to speech, $0.09 per 1K chars
- [Qwen 3.6](https://tryinfer.com/models/qwen3.6): Chat, $1.30 in · $7.80 out per 1M tokens (≤128K ctx)
- [MiniMax H3](https://tryinfer.com/models/hailuo-03): Image to video, $0.13 per second
- [Nano Banana 2 Lite](https://tryinfer.com/models/nano-banana-2-lite): Edit, $0.034 per image
- [Seedream 5.0 Pro](https://tryinfer.com/models/seedream-5.0-pro): Edit, $0.09 per image
- [Qwen 3.6 27B](https://tryinfer.com/models/qwen3.6-27b): Chat, $0.29 in · $1.95 out per 1M tokens (≤256K ctx)
- [DeepSeek V4 Flash](https://tryinfer.com/models/deepseek4-flash): Chat, $0.11 in · $0.66 out per 1M tokens (≤256K ctx)
- [Qwen 3.8 27B](https://tryinfer.com/models/qwen3.8-27b): Chat, $0.20 in · $2.50 out per 1M tokens (≤256K ctx)
- [Qwen 3.7 Max Preview](https://tryinfer.com/models/qwen3.7-max-preview): Chat, $1.30 in · $7.80 out per 1M tokens (≤128K ctx)
- [MiniMax-M3](https://tryinfer.com/models/minimax-m3): Chat, $0.30 in · $1.20 out per 1M tokens (≤512K ctx)
- [DeepSeek V4.1 Flash 0910](https://tryinfer.com/models/deepseek41-flash): Chat, $0.30 in · $1.20 out per 1M tokens (≤1M ctx)
- [Reka Edge 2603](https://tryinfer.com/models/reka-edge-2603): Chat, $0.10 in · $0.10 out per 1M tokens (≤16K ctx)
- [DeepSeek V4.1 Flash 1017](https://tryinfer.com/models/deepseek41-flash-20261017): Chat, $0.15 in · $0.60 out per 1M tokens (≤1M ctx)
- [Reka Flash 3](https://tryinfer.com/models/reka-flash-3): Chat, $0.10 in · $0.20 out per 1M tokens (≤64K ctx)
- [GLM 5.3 Flash](https://tryinfer.com/models/glm5.3-flash): Chat, $0.15 in · $0.50 out per 1M tokens (≤256K ctx)
- [GLM 5.3](https://tryinfer.com/models/glm5.3): Chat, $1.17 in · $3.96 out per 1M tokens (≤256K ctx)
## API
Base URL: https://api.tryinfer.com
- POST https://api.tryinfer.com/v1/inference/{model_id}/{capability} — run any async model (image, video, edit, audio). Each model page documents its input schema, parameters, and copy-paste code samples.
- POST https://api.tryinfer.com/v1/chat/completions — OpenAI-compatible chat completions; set `model` to a chat model_id.
Browse every model: https://tryinfer.com/models
API docs: https://tryinfer.com/console/docs