Providers
Esta página aún no está disponible en tu idioma.
GreatRouter integrates 792 providers in the full catalog. 101 providers have routable models (featured or standard visibility) ready for auto-routing.
Infrastructure Backends
Inference requests are routed through these infrastructure backends depending on where the model is hosted:
| Backend | Protocol | Models served |
|---|---|---|
| Cloudflare Workers AI | env.AI.run() direct binding | ~73 models (Llama, Gemma, Flux, Whisper, etc.) |
| Cloudflare AI Gateway | REST API at /client/v4/accounts/{id}/ai/run | Primary path — all major providers (OpenAI, Google, Meta, xAI, etc.) |
| Fal AI | Via Cloudflare AI Gateway (fal provider) | ~200+ models hosted on Fal |
| HuggingFace Inference Providers | REST API at router.huggingface.co | ~400+ community and research models |
| Suno | Suno API at api.sunoapi.org | Music generation (V4, V5 models) |
The auto-router selects the best backend per model based on the registry configuration. Models defined with cloudflare.gateway go through AI Gateway unified billing. Models with routing.source: fal are routed via Fal. Models with routing.source: huggingface go through HuggingFace Inference Providers. Music tasks route to Suno when routing.source: suno is set.
Bria
Bria provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bria Video Eraser | Text To Video | $0.140 | per second |
| Bria Video Eraser Erase Mask | Text To Video | $0.140 | per second |
| Bria Video Eraser | Text To Video | $0.140 | per second |
| Embed Product | Image To Image | $0.040 | per images |
| Fibo Bbq Preview | Text To Image | $0.040 | per images |
| Fibo Edit [Add Object by Text] | Image To Image | $0.040 | per images |
| Fibo Edit [Blend] | Image To Image | $0.040 | per images |
| Fibo Edit [Colorize] | Image To Image | $0.040 | per images |
| Fibo Edit | Image To Image | $0.040 | per images |
| Fibo Edit [Erase by Text] | Image To Image | $0.040 | per images |
| Fibo Edit [Relight] | Image To Image | $0.040 | per images |
| Fibo Edit [Replace Object by Text] | Image To Image | $0.040 | per images |
| Fibo Edit [Reseason] | Image To Image | $0.040 | per images |
| Fibo Edit [Restore] | Image To Image | $0.040 | per images |
| Fibo Edit [Restyle] | Image To Image | $0.040 | per images |
| Fibo Edit [Rewrite Text] | Image To Image | $0.040 | per images |
| Fibo Edit [Sketch to Image] | Image To Image | $0.040 | per images |
| Fibo | Text To Image | $0.040 | per images |
| Fibo Lite | Text To Image | $0.036 | per images |
| Replace Background | Image To Image | $0.040 | per images |
| Upscale | Image To Image | $0.040 | per images |
| Video | Text To Video | $0.140 | per second |
| Bria Video Eraser | Text To Video | $0.140 | per second |
| Bria Video Eraser Erase Mask | Text To Video | $0.140 | per second |
| Bria Video Eraser | Text To Video | $0.140 | per second |
| Video | Text To Video | $0.140 | per second |
Helsinki NLP
Helsinki NLP provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Opus Mt Ar En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt De En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Ar | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En De | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Es | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Fr | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Hi | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En It | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Ru | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt En Zh | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Es En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Fr En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt It En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Ja En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Ko En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Ru En | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Ar | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Es | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Fr | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En It | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Ko | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Pt | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Tc Big En Tr | Translation | $0.080 in / $0.320 out | per 1M tokens |
| Opus Mt Zh En | Translation | $0.080 in / $0.320 out | per 1M tokens |
Openai
OpenAI builds GPT-5.x, GPT-Image, Whisper, and TTS — the broadest commercial frontier model lineup.
| Model | Type | Price | Unit |
|---|---|---|---|
| GPT-4.1 | Text Generation | $2.00 in / $8.00 out | per 1M tokens |
| GPT-4.1 Mini | Text Generation | $0.400 in / $1.60 out | per 1M tokens |
| GPT-4o Transcribe | Automatic Speech Recognition | $0.0060 | per audio minute |
| GPT-5 | Text Generation | $1.25 in / $10.00 out | per 1M tokens |
| GPT-5.4 | Text Generation | $2.50 in / $15.00 out | per 1M tokens |
| GPT-5.4 Mini | Text Generation | $0.750 in / $4.50 out | per 1M tokens |
| GPT-5.4 Nano | Text Generation | $0.200 in / $1.25 out | per 1M tokens |
| GPT-5.4 Pro | Text Generation | $30.00 in / $180.00 out | per 1M tokens |
| GPT-5.5 | Text Generation | $5.00 in / $30.00 out | per 1M tokens |
| GPT-5.5 Pro | Text Generation | $30.00 in / $180.00 out | per 1M tokens |
| GPT Image 1.5 | Text Generation | $5.00 in / $10.00 out | per 1M tokens |
| GPT Image 2 | Text Generation | $5.00 in / $10.00 out | per 1M tokens |
| GPT Image 2 API | Image To Image | $1.00 | per request |
| GPT-OSS 120B | Text Generation | $0.350 in / $0.750 out | per 1M tokens |
| GPT-OSS 20B | Text Generation | $0.200 in / $0.300 out | per 1M tokens |
| Gpt Oss Safeguard 20b | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| o4-mini | Text Generation | $1.10 in / $4.40 out | per 1M tokens |
| TTS-1 | Text To Speech | $0.000015 | per character |
| TTS-1 HD | Text To Speech | $0.000030 | per character |
| Whisper | Automatic Speech Recognition | $0.0005 | per 1M input tokens |
| Whisper Large V3 Turbo | Automatic Speech Recognition | $0.0005 | per 1M input tokens |
| Whisper Tiny En | Automatic Speech Recognition | $0.0005 | per 1M input tokens |
Google ai studio
Google ai studio provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Embeddinggemma 300m | Text Embeddings | $0.010 | per 1M input tokens |
| Gemini 2.5 Flash | Text Generation | $0.300 in / $2.50 out | per 1M tokens |
| Gemini 2.5 Flash Lite | Text Generation | $0.100 in / $0.400 out | per 1M tokens |
| Gemini 2.5 Pro | Text Generation | $1.25 in / $10.00 out | per 1M tokens |
| Gemini 3 Flash | Text Generation | $0.500 in / $3.00 out | per 1M tokens |
| Gemini 3.1 Flash Lite | Text Generation | $0.250 in / $1.50 out | per 1M tokens |
| Gemini 3.1 Flash TTS | Text To Speech | $3.00, $0.750, $12.00, $4.50 | per 1M input audio tokens; per 1M input text tokens; per 1M output audio tokens; per 1M output text tokens |
| Gemini 3.1 Pro | Text Generation | $1.25 in / $5.00 out | per 1M tokens |
| Gemma 2b It Lora | Text Generation | $0.010 | per 1M input tokens |
| Gemma 3 12b It | Text Generation | $0.350 in / $0.560 out | per 1M tokens |
| Gemma 4 26B A4B IT | Text Generation | $0.100 in / $0.300 out | per 1M tokens |
| Gemma 7b It | Text Generation | $0.050 | per 1M tokens |
| Gemma 7b It Lora | Text Generation | $0.050 | per 1M input tokens |
| Imagen 4 | Text To Image | $0.040 | per image |
| Nano Banana | Text To Image | $0.300 in / $30.00 out | per 1M tokens |
| Nano Banana 2 | Text To Image | $0.500 in / $60.00 out | per 1M tokens |
| Nano Banana Pro | Text To Image | $2.00 in / $120.00 out | per 1M tokens |
| Veo 3 | Text To Video | $0.200, $0.200, $0.200, $0.400, $0.400 | per second @ 720p; per second @ 1080p; per second (default); per second @ 1080p with audio; per second @ 720p with audio |
| Veo 3 Fast | Text To Video | $0.080, $0.100, $0.100, $0.120, $0.300, $0.100 | per second @ 720p; per second @ 1080p; per second (default); per second @ 1080p with audio; per second @ 4K with audio; per second @ 720p with audio |
| Veo 3.1 | Text To Video | $0.200, $0.200, $0.400, $0.400, $0.400, $0.600, $0.400 | per second @ 720p; per second @ 1080p; per second (default); per second @ 1080p with audio; per second @ 4K; per second @ 4K with audio; per second @ 720p with audio |
| Veo 3.1 Fast | Text To Video | $0.080, $0.100, $0.080, $0.120, $0.250, $0.300, $0.100 | per second @ 720p; per second @ 1080p; per second (default); per second @ 1080p with audio; per second @ 4K; per second @ 4K with audio; per second @ 720p with audio |
Xai
xAI builds Grok — real-time-knowledge models with strong reasoning, plus Grok Imagine for image and video generation.
| Model | Type | Price | Unit |
|---|---|---|---|
| Grok 4.20 0309 Non Reasoning | Text Generation | $2.00 in / $6.00 out | per 1M tokens |
| Grok 4.20 0309 Reasoning | Text Generation | $2.00 in / $6.00 out | per 1M tokens |
| Grok 4.20 Multi Agent 0309 | Text Generation | $2.00 in / $6.00 out | per 1M tokens |
| Grok 4.3 | Text Generation | $1.25 in / $2.50 out | per 1M tokens |
| Grok Imagine Image | Text To Image | $0.020, $0.0020 | per image; per input image |
| Grok Imagine Image | Image To Image | $0.020 | per images |
| Grok Imagine Image Quality | Text To Image | $0.050, $0.010 | per image; per input image |
| Grok Imagine Image Editing Quality | Image To Image | $0.0002 | per compute second |
| Grok Imagine Image | Text To Image | $0.0002 | per compute second |
| Grok Imagine Video | Text To Video | $0.050 | per second (default) |
| Grok Imagine Video 1.5 Preview | Text To Video | $0.080, $0.140 | per second (default); per second 720p |
| Grok Imagine Video | Text To Video | $0.050 | per second |
| Grok Imagine Extend Video | Text To Video | $0.050 | per second |
| Grok Imagine Video | Image To Video | $0.050 | per second |
| Grok Imagine Reference to Video | Image To Video | $0.050 | per second |
| Grok Imagine Video | Text To Video | $0.050 | per second |
| Grok Imagine Video 1.5 | Image To Video | $0.010 | per second |
| Grok STT | Automatic Speech Recognition | $0.0017 | per audio minute |
| Grok TTS | Text To Speech | $0.000015 | per character |
| Grok Voice | Text To Speech | $0.050, $0.0040 | per audio minute; per text message |
| xAI Text to Speech | Text To Speech | $0.000070 | per compute second |
Meta
Meta’s open-weight LLaMA family powers the majority of open-source LLM applications, plus MusicGen and NLLB for translation.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bart Large Cnn | Text Generation | $0 | per 1M input tokens |
| Llama 3.1 70b Instruct | Text Generation | $0.010 | per 1M tokens |
| Llama 3.1 8b Instruct | Text Generation | $0.280 in / $0.830 out | per 1M tokens |
| Llama 3.1 8b Instruct Fast | Text Generation | $0.150 in / $0.290 out | per 1M tokens |
| Llama 3.1 8b Instruct Fp8 | Text Generation | $0.152 in / $0.287 out | per 1M tokens |
| Llama 3.2 11b Vision Instruct | Text Generation | $0.049 in / $0.676 out | per 1M tokens |
| Llama 3.2 11B Vision VQA | Image To Text | $0.049 in / $0.676 out | per 1M tokens |
| Llama 3.2 1b Instruct | Text Generation | $0.027 in / $0.201 out | per 1M tokens |
| Llama 3.2 3b Instruct | Text Generation | $0.051 in / $0.335 out | per 1M tokens |
| Llama 3.3 70b Instruct Fp8 Fast | Text Generation | $0.293 in / $2.25 out | per 1M tokens |
| Llama 4 Scout 17b 16e Instruct | Text Generation | $0.270 in / $0.850 out | per 1M tokens |
| Llama 4 Scout 17B Vision VQA | Image To Text | $0.270 in / $0.850 out | per 1M tokens |
| Llama Guard 3 8b | Text Generation | $0.484 in / $0.030 out | per 1M tokens |
| M2m100 1.2b | Translation | $0.342 | per 1M tokens |
| Llama 2 7b Chat Hf Lora | Text Generation | $0.060 | per 1M input tokens |
Bytedance
ByteDance develops the Seedance video models and Seedream image models, with strong motion and compositional quality.
| Model | Type | Price | Unit |
|---|---|---|---|
| Lynx | Image To Video | $0.600 | per second |
| Seedance 2.0 | Text To Video | $0.220, $0.550, $0.220 | per second @ 720p; per second @ 1080p; per second (default) |
| Seedance 2.0 Fast | Text To Video | $0.080, $0.170, $0.080 | per second @ 720p; per second @ 1080p; per second (default) |
| Seedance 2.0 Fast Image to Video | Image To Video | $0.011 | per request |
| Seedance 2.0 Fast Reference to Video | Image To Video | $0.011 | per request |
| Seedance 2.0 Fast Text to Video | Text To Video | $0.011 | per request |
| Seedance 2 Image to Video | Image To Video | $0.014 | per request |
| Seedance 2 Reference to Video | Image To Video | $0.014 | per request |
| Seedance 2.0 Text to Video API | Text To Video | $0.014 | per request |
| Seedream 4.0 | Text To Image | $0.030 | per image |
| Seedream 4.5 | Text To Image | $0.040 | per image |
| Seedream 5 Lite | Text To Image | $0.035 | per image |
| Stable Diffusion Xl Lightning | Text To Image | $0.035 | per image |
Recraft
Recraft specializes in vector and raster image generation for design and branding workflows.
| Model | Type | Price | Unit |
|---|---|---|---|
| Recraftv3 | Text To Image | $0.040 | per image |
| Recraftv4 | Text To Image | $0.040 | per image |
| Recraftv4 1 | Text To Image | $0.040 | per image |
| Recraftv4 1 Pro | Text To Image | $0.250 | per image |
| Recraftv4 1 Pro Vector | Text To Image | $0.300 | per image |
| Recraftv4 1 Utility | Text To Image | $0.040 | per image |
| Recraftv4 1 Utility Pro | Text To Image | $0.250 | per image |
| Recraftv4 1 Utility Pro Vector | Text To Image | $0.300 | per image |
| Recraftv4 1 Utility Vector | Text To Image | $0.080 | per image |
| Recraftv4 1 Vector | Text To Image | $0.080 | per image |
| Recraftv4 Pro | Text To Image | $0.250 | per image |
| Recraftv4 Pro Vector | Text To Image | $0.300 | per image |
| Recraftv4 Vector | Text To Image | $0.080 | per image |
Unsloth
Unsloth provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| DeepSeek R1 Distill Qwen 1.5B | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Gemma 3 12b It | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Gemma 3 12b It Qat | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3 8b | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3 8b Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.1 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.2 3B | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Llama 3.2 3B Instruct | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Meta Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Mistral Small 24B Instruct 2501 | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Qwen2.5 32B Instruct | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
Alibaba
Alibaba Cloud offers the Qwen family of large language models and the Wan video/image generation models with strong multilingual support.
| Model | Type | Price | Unit |
|---|---|---|---|
| Happy Horse | Image To Video | $0.140 | per second |
| Happy Horse | Image To Video | $0.140 | per second |
| Happy Horse | Text To Video | $0.140 | per second |
| Happy Horse Video Edit | Text To Video | $0.140 | per second |
| Hh1 I2v | Image To Video | $0.140, $0.280, $0.280 | per second @ 720p; per second @ 1080p; per second (default) |
| Hh1 T2v | Text To Video | $0.140, $0.280, $0.280 | per second @ 720p; per second @ 1080p; per second (default) |
| Qwen3 Max | Text Generation | $1.25 in / $5.00 out | per 1M tokens |
| Qwen3.5 397b A17b | Text Generation | $1.50 in / $6.00 out | per 1M tokens |
| Wan 2.6 Image | Text To Image | $0.030 | per image |
| Wan 2.7 I2v | Image To Video | $0.100, $0.150, $0.100 | per second @ 720p; per second @ 1080p; per second (default) |
Veed
Veed provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Avatars | Text To Video | $0.0006 | per compute second |
| Avatars | Text To Video | $0.0006 | per compute second |
| Fabric 1.0 | Image To Video | $0.0002 | per compute second |
| Fabric 1.0 Fast | Image To Video | $0.0002 | per compute second |
| Fabric 1.0 | Text To Video | $0.0002 | per compute second |
| Lipsync | Text To Video | $0.0006 | per compute second |
| Subtitles | Text To Video | $0.000070 | per compute second |
| Video Background Removal | Text To Video | $0.0013 | per compute second |
| Video Background Removal | Text To Video | $0.0013 | per compute second |
| Video Background Removal | Text To Video | $0.0013 | per compute second |
Meta llama
Meta llama provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3.1 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.2 3B | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Llama 3.2 3B Instruct | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Llama 4 Scout 17B 16E Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama Guard 3 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama Guard 2 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Qwen
Qwen provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Qwen2.5 32B Instruct | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
| Qwen2.5 Coder 0.5B Instruct | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Qwen2.5 Coder 1.5B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Qwen2.5 Coder 14B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Qwen2.5 Coder 32B | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
| Qwen2.5 Coder 3B Instruct | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Qwen2.5 Coder 7B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Qwen3.5 397B A17B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| QwQ 32B Preview | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
Mirelo ai
Mirelo ai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Mirelo SFX | Music Generation | $0.0013 | per compute second |
| Mirelo SFX | Text To Video | $0.0013 | per compute second |
| Mirelo SFX V1.5 | Music Generation | $0.0013 | per compute second |
| Mirelo SFX V1.5 | Text To Video | $0.0013 | per compute second |
| Mirelo SFX1.6 | Music Generation | $0.0013 | per compute second |
| Mirelo SFX1.6 | Music Generation | $0.0013 | per compute second |
| Mirelo SFX1.6 | Music Generation | $0.0013 | per compute second |
| Mirelo SFX1.6 | Text To Video | $0.0013 | per compute second |
Nvidia
NVIDIA provides Nemotron — high-performance language models optimized for inference.
| Model | Type | Price | Unit |
|---|---|---|---|
| Canary 1b Flash | Automatic Speech Recognition | $0.0016 | per minute |
| Cosmos 3 Super Image to Video | Image To Video | $0.050 | per second |
| Cosmos 3 Super | Text To Image | $0.040 | per images |
| Llama 3.1 70B Instruct FP8 | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
| Llama 3.1 8B Instruct FP8 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Nemotron 3 120b A12b | Text Generation | $0.500 in / $1.50 out | per 1M tokens |
| Nemotron 3 Nano Omni | Text Generation | $0.010 | per 1000 tokens |
| NVIDIA Nemotron 3 Super 120B A12B BF16 | Text Generation | $0.256 in / $1.02 out | per 1M tokens |
Rundiffusion fal
Rundiffusion fal provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Juggernaut Flux Base | Text To Image | $0.0013 | per compute second |
| Juggernaut Flux Base | Image To Image | $0.0013 | per compute second |
| Juggernaut Flux Lightning | Text To Image | $0.0013 | per compute second |
| Juggernaut Flux Base LoRA | Text To Image | $0.0013 | per compute second |
| Juggernaut Flux Lora | Image To Image | $0.0013 | per compute second |
| Juggernaut Flux Pro | Text To Image | $0.0013 | per compute second |
| Juggernaut Flux Pro | Image To Image | $0.0013 | per compute second |
| Rundiffusion Photo Flux | Text To Image | $0.045 | per megapixel |
Anthropic
Anthropic builds Claude — frontier models known for long-context reasoning, nuanced conversation, and safe agentic behavior.
| Model | Type | Price | Unit |
|---|---|---|---|
| Claude Haiku 4.5 | Text Generation | $1.00 in / $5.00 out | per 1M tokens |
| Claude Opus 4.6 | Text Generation | $5.00 in / $25.00 out | per 1M tokens |
| Claude Opus 4.7 | Text Generation | $5.00 in / $25.00 out | per 1M tokens |
| Claude Opus 4.8 | Text Generation | $5.00 in / $25.00 out | per 1M tokens |
| Claude Sonnet 4 | Text Generation | $3.00 in / $15.00 out | per 1M tokens |
| Claude Sonnet 4.5 | Text Generation | $3.00 in / $15.00 out | per 1M tokens |
| Claude Sonnet 4.6 | Text Generation | $3.00 in / $15.00 out | per 1M tokens |
BAAI
BAAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bge Base En | Text Embeddings | $0.010 | per 1M input tokens |
| Bge Base Zh V1.5 | Text Embeddings | $0.010 | per 1M input tokens |
| Bge Large En | Text Embeddings | $0.018 | per 1M input tokens |
| Bge Large Zh V1.5 | Text Embeddings | $0.018 | per 1M input tokens |
| Bge Reranker V2 M3 | Text Classification | $0.050 | per 1M tokens |
| Bge Small En | Text Embeddings | $0.0055 | per 1M input tokens |
| Bge Small Zh V1.5 | Text Embeddings | $0.0055 | per 1M input tokens |
Black forest labs
Black Forest Labs created Flux — state-of-the-art text-to-image models with photorealistic quality and fast inference.
| Model | Type | Price | Unit |
|---|---|---|---|
| Flux 1 Schnell | Text To Image | $0.000053 | per 1M input tokens |
| Flux 2 Dev | Text To Image | $0.0002, $0.0004 | per input tile-step; per output tile-step |
| Flux 2 Flex | Text To Image | $0.050, $0.050, $0.050 | per 1M additional output tokens; per 1M tokens (first output); per 1M input tokens |
| Flux 2 Klein 4b | Text To Image | $0.000059, $0.0003 | per input tile; per output tile |
| Flux 2 Klein 9b | Text To Image | $0.015, $0.0020, $0.0020 | per image; per 1M additional tokens; input image per mp |
| Flux 2 Max | Text To Image | $0.030, $0.070, $0.030 | per 1M additional output tokens; per 1M tokens (first output); per 1M input tokens |
| Flux 2 Pro Preview | Text To Image | $0.015, $0.030, $0.015 | per 1M additional output tokens; per 1M tokens (first output); per 1M input tokens |
Minimax
MiniMax offers Hailuo for video generation, M2/M3 language models, music generation, and expressive speech synthesis.
| Model | Type | Price | Unit |
|---|---|---|---|
| Hailuo 2.3 | Text To Video | $0.047, $0.560, $0.490, $0.280 | per second (default); per 10s clip @ 768p; per 6s clip @ 1080p; per 6s clip @ 768p |
| Hailuo 2.3 Fast | Text To Video | $0.032, $0.320, $0.330, $0.190 | per second (default); per 10s clip @ 768p; per 6s clip @ 1080p; per 6s clip @ 768p |
| M2.7 | Text Generation | $0.300 in / $1.20 out | per 1M tokens |
| MiniMax M3 | Text Generation | $0.060, $0.240, $1.20, $0.300, $4.80, $1.20 | per 1M cached input tokens; per 1M cached input tokens (extended); per 1M input tokens (extended); per 1M input tokens (standard); per 1M output tokens (extended); per 1M output tokens (standard) |
| Music 2.6 | Music Generation | $0.150, $0.010 | per track; per lyrics generation |
| Speech 2.8 Hd | Text To Speech | $0.0001 | per character |
| Speech 2.8 Turbo | Text To Speech | $0.000060 | per character |
Wan
Wan provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Wan v2.6 Image to Image | Image To Image | $0.000070 | per compute second |
| Wan v2.6 Image to Video | Image To Video | $0.100 | per second |
| V2.6 | Image To Video | $0.050 | per second |
| Wan v2.6 Reference to Video | Text To Video | $0.100 | per second |
| V2.6 | Text To Video | $0.000070 | per compute second |
| Wan v2.6 Text to Image | Text To Image | $0.000070 | per compute second |
| Wan v2.6 Text to Video | Text To Video | $0.100 | per second |
Zai org
Z.ai develops GLM — bilingual English/Chinese language models with strong tool-use capabilities.
| Model | Type | Price | Unit |
|---|---|---|---|
| GLM 4.5 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| GLM 4.6 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| GLM 4.6V Flash | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| GLM 4.7 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Glm 4.7 Flash | Text Generation | $0.060 in / $0.400 out | per 1M tokens |
| GLM 5 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| GLM 5.1 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Baai
BAAI (Beijing Academy of Artificial Intelligence) develops the BGE family of embedding and reranker models for retrieval.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bge Base En V1.5 | Text Embeddings | $0.067 | per 1M input tokens |
| Bge Large En V1.5 | Text Embeddings | $0.204 | per 1M input tokens |
| Bge M3 | Text Embeddings | $0.012 | per 1M input tokens |
| Bge Reranker Base | Text Classification | $0.0031 | per 1M input tokens |
| Bge Small En V1.5 | Text Embeddings | $0.020 | per 1M input tokens |
Deepgram
Deepgram provides industry-leading speech-to-text and text-to-speech with high accuracy and low latency.
| Model | Type | Price | Unit |
|---|---|---|---|
| Aura 1 | Text To Speech | $0.015 | per 1M input tokens |
| Aura 2 En | Text To Speech | $0.030 | per 1M input tokens |
| Aura 2 Es | Text To Speech | $0.030 | per 1M input tokens |
| Flux | Automatic Speech Recognition | $0.0077 | per 1M input tokens |
| Nova 3 | Automatic Speech Recognition | $0.0052 | per 1M input tokens |
Deepseek ai
DeepSeek builds frontier reasoning models at a fraction of the cost of closed alternatives.
| Model | Type | Price | Unit |
|---|---|---|---|
| DeepSeek R1 Distill Qwen 1.5B | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Deepseek R1 Distill Qwen 32b | Text Generation | $0.497 in / $4.88 out | per 1M tokens |
| DeepSeek R1 Distill Qwen 7B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| DeepSeek V4 Flash | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| DeepSeek V4 Pro | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Huihui ai
Huihui ai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| DeepSeek R1 Distill Qwen 32B Abliterated | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
| Gemma 3 12b It Abliterated | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.2 3B Instruct Abliterated | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
| Meta Llama 3.1 8B Instruct Abliterated | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Qwen2.5 Coder 32B Instruct Abliterated | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
Mistralai
Mistral AI’s Small models deliver frontier performance at low cost.
| Model | Type | Price | Unit |
|---|---|---|---|
| Mistral 7b Instruct V0.1 | Text Generation | $0.110 in / $0.190 out | per 1M tokens |
| Mistral 7b Instruct V0.2 | Text Generation | $0.050 | per 1M tokens |
| Mistral 7b Instruct V0.2 Lora | Text Generation | $0.050 | per 1M input tokens |
| Mistral Small 3.1 24b Instruct | Text Generation | $0.351 in / $0.555 out | per 1M tokens |
| Mistral Small 3.1 24B Vision | Image To Text | $0.351 in / $0.555 out | per 1M tokens |
Openrouter
Openrouter provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| OpenRouter | Text Generation | $0.010 | per request |
| OpenRouter Chat Completions [OpenAI Compatible] | Text Generation | $0.010 | per request |
| OpenRouter Embeddings [OpenAI Compatible] | Text Generation | $0.010 | per compute second |
| OpenRouter Responses [OpenAI Compatible] | Text Generation | $0.010 | per compute second |
| OpenRouter [Vision] | Image To Text | $0.010 | per request |
MiniMaxAI
MiniMaxAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| MiniMax M2 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| MiniMax M2.1 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| MiniMax M2.5 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| MiniMax M2.7 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
RedHatAI
RedHatAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3 70B Instruct FP8 | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
| Meta Llama 3 8B Instruct FP8 | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3 8B Instruct FP8 KV | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Meta AI’s open-source NLP models, including BART for summarization.
| Model | Type | Price | Unit |
|---|---|---|---|
| Mbart Large 50 Many To Many Mmt | Translation | $0.140 in / $0.560 out | per 1M tokens |
| Nllb 200 1.3b | Translation | $0.044 in / $0.176 out | per 1M tokens |
| Nllb 200 3.3b | Translation | $0.044 in / $0.176 out | per 1M tokens |
| Nllb 200 Distilled 600m | Translation | $0.080 in / $0.320 out | per 1M tokens |
Imagineart
Imagineart provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Imagineart 1.5 Preview | Text To Image | $0.000030 | per compute second |
| ImagineArt 1.5 Pro Preview | Text To Image | $0.000070 | per compute second |
| Imagineart 2.0 Edit Preview | Image To Image | $0.000070 | per compute second |
| Imagineart 2.0 Preview | Text To Image | $0.000070 | per compute second |
Microsoft
Microsoft provides specialized models including ResNet-50 for image classification.
| Model | Type | Price | Unit |
|---|---|---|---|
| Mai Image 2.5 Text to Image | Text To Image | $0.000070 | per compute second |
| Mai Image 2.5 | Image To Image | $1.00 | per credits |
| Resnet 50 | Image Classification | $0.000003 | per 1M input tokens |
| Speecht5 Tts | Text To Speech | $0.000012 | per character |
Moonshotai
Moonshot AI builds Kimi — long-context language models with strong agentic and reasoning capabilities.
| Model | Type | Price | Unit |
|---|---|---|---|
| Kimi K2 Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Kimi K2 Thinking | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Kimi K2.5 | Text Generation | $0.600 in / $3.00 out | per 1M tokens |
| Kimi K2.6 | Text Generation | $0.950 in / $4.00 out | per 1M tokens |
Moonvalley
Moonvalley provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Marey Realism V1.5 | Image To Video | $1.50 | per 5 seconds |
| Marey Realism V1.5 | Text To Video | $2.00 | per request |
| Marey Realism V1.5 | Text To Video | $2.00 | per request |
| Marey Realism V1.5 | Text To Video | $1.50 | per 5 seconds |
Qwen
Alibaba’s Qwen team develops Qwen2.5 Coder, Qwen3, and QwQ for coding and reasoning.
| Model | Type | Price | Unit |
|---|---|---|---|
| Qwen2.5 Coder 32b Instruct | Text Generation | $0.660 in / $1.00 out | per 1M tokens |
| Qwen3 30b A3b Fp8 | Text Generation | $0.051 in / $0.335 out | per 1M tokens |
| Qwen3 Embedding 0.6b | Text Embeddings | $0.012 | per 1M input tokens |
| Qwq 32b | Text Generation | $0.660 in / $1.00 out | per 1M tokens |
Cassetteai
Cassetteai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| music generator | Music Generation | $0.0013 | per compute second |
| Sound Effects Generator | Music Generation | $0.0013 | per compute second |
| Video Sound Effects Generator | Text To Video | $0.0013 | per compute second |
Decart
Decart provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Lucy Edit [Pro] | Text To Video | $0.100 | per second |
| Lucy Restyle | Text To Video | $0.010 | per second |
| Lucy 2.1 VTON Realtime | Text To Video | $0.020 | per second |
Inworld
Inworld develops expressive text-to-speech models optimized for games, media, and conversational AI.
| Model | Type | Price | Unit |
|---|---|---|---|
| Tts 1.5 Max | Text To Speech | $0.000035 | per character |
| Tts 1.5 Mini | Text To Speech | $0.000025 | per character |
| Tts 2 | Text To Speech | $0.000035 | per character |
Krea
Krea provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Krea 2 Large | Text To Image | $0.0010 | per request |
| Krea 2 Medium | Text To Image | $0.0010 | per request |
| Krea 2 Medium Text to Image Turbo | Text To Image | $0.0010 | per request |
Runwayml
Runway builds Gen — frontier video generation models used in film, advertising, and creative production.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gen 4.5 | Text To Video | $0.120 | per second (default) |
| Stable Diffusion V1 5 Img2img | Text To Image | $0.035 | per image |
| Stable Diffusion V1 5 Inpainting | Text To Image | $0.035 | per image |
Suno
Suno provides frontier music generation models (V4.5, V5) routed via the Suno API with async polling.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bark Small | Text To Speech | $0.000007 | per character |
| Suno V4.5 All | Music Generation | $0.240 | per generation |
| Suno V5 | Music Generation | $0.280 | per generation |
NousResearch
NousResearch provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Meta Llama 3 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
VAGOsolutions
VAGOsolutions provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3 SauerkrautLM 8b Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Llama 3.1 SauerkrautLM 8b Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Argil
Argil provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Avatars Audio to Video | Text To Video | $0.0013 | per compute second |
| Avatars Text to Video | Text To Video | $0.0013 | per compute second |
Clarityai
Clarityai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Crystal Upscaler | Image To Image | $0.016 | per megapixel |
| Crystal Upscaler [Video] | Text To Video | $1.00 | per request |
Google offers the Gemini family of multimodal models, Imagen for image generation, Veo for video, and Gemma for open weights.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12B IT Vision | Image To Text | $0.350 in / $0.560 out | per 1M tokens |
| Vit Base Patch16 224 | Image Classification | $0.0040 | per image |
Google t5
Google t5 provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| T5 Base | Translation | $0.080 in / $0.320 out | per 1M tokens |
| T5 Small | Translation | $0.044 in / $0.176 out | per 1M tokens |
Ideogram
Ideogram provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Ideogram V4.0q Text to Image | Text To Image | $0.010 | per request |
| Ideogram V4.0q Text to Image (LoRA) | Text To Image | $0.010 | per request |
Leonardo
Leonardo.AI builds creative image generation models with strong artistic style control.
| Model | Type | Price | Unit |
|---|---|---|---|
| Lucid Origin | Text To Image | $0.0070 | per 1M input tokens |
| Phoenix 1.0 | Text To Image | $0.0058 | per 1M input tokens |
Mlabonne
Mlabonne provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Abliterated | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
| Meta Llama 3.1 8B Instruct Abliterated | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Perceptron
Perceptron provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Isaac 0.1 | Image To Text | $1.00 | per request |
| Isaac 0.1 [OpenAI Compatible Endpoint] | Image To Text | $1.00 | per request |
Pixverse
PixVerse offers high-quality text-to-video with strong motion consistency.
| Model | Type | Price | Unit |
|---|---|---|---|
| V5.6 | Text To Video | $0.080, $0.385, $0.610, $0.385, $0.610, $0.495, $0.720, $0.375, $0.750, $0.175, $0.400, $0.175, $0.450, $0.225, $0.400, $0.750, $0.975, $0.350, $0.575, $0.350, $0.575, $0.450, $0.675 | per second (default); per 10s clip @ 360p; per 10s clip @ 360p with audio; per 10s clip @ 540p; per 10s clip @ 540p with audio; per 10s clip @ 720p; per 10s clip @ 720p with audio; per 5s clip @ 1080p; per 5s clip @ 1080p with audio; per 5s clip @ 360p; per 5s clip @ 360p with audio; per 5s clip @ 540p; per 5s clip @ 540p with audio; per 5s clip @ 720p; per 5s clip @ 720p with audio; per 8s clip @ 1080p; per 8s clip @ 1080p with audio; per 8s clip @ 360p; per 8s clip @ 360p with audio; per 8s clip @ 540p; per 8s clip @ 540p with audio; per 8s clip @ 720p; per 8s clip @ 720p with audio |
| V6 | Text To Video | $0.045, $0.090, $0.060, $0.115, $0.025, $0.035, $0.035, $0.045, $0.060 | per second @ 720p; per second @ 1080p; per second (default); per second @ 1080p with audio; per second @ 360p; per second @ 360p with audio; per second @ 540p; per second @ 540p with audio; per second @ 720p with audio |
Sonilo
Sonilo provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Sonilo V1.1 Text to Music | Music Generation | $0.0025 | per second |
| V1.1 | Music Generation | $0.0090 | per second |
Vidu
Vidu offers high-fidelity text-to-video with strong character and scene consistency.
| Model | Type | Price | Unit |
|---|---|---|---|
| Q3 Pro | Text To Video | $0.125, $0.150, $0.125, $0.050 | per second @ 720p; per second @ 1080p; per second (default); per second @ 540p |
| Q3 Turbo | Text To Video | $0.060, $0.070, $0.060, $0.040 | per second @ 720p; per second @ 1080p; per second (default); per second @ 540p |
ChuGyouk
ChuGyouk provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3.1 8B | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
DeSTA ntu
DeSTA ntu provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
DreamFast
DreamFast provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Heretic | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Falconsai
Falconsai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Nsfw_image_detection | Image Classification | $0.0040 | per image |
GraySwanAI
GraySwanAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3 8B Instruct RR | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
HiTZ
HiTZ provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Latxa Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
INSAIT Institute
INSAIT Institute provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| BgGPT Gemma 3 12B IT | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
LumiOpen
LumiOpen provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama Poro 2 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
NCSOFT
NCSOFT provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama VARCO 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Pramodmunje
Pramodmunje provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Text To Image | Text To Image | $0.018 | per image |
ProsusAI
ProsusAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Finbert | Text Classification | $0.050 | per 1M tokens |
SEACrowd
SEACrowd provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma SEA LION V4 27B VL | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
Sabomako
Sabomako provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Heretic | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Systran
Systran provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Faster Whisper Large V3 | Automatic Speech Recognition | $0.0053 | per minute |
TroyDoesAI
TroyDoesAI provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3.1 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
ZB Tech
ZB Tech provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Text To Image | Text To Image | $0.018 | per image |
Ai4bharat
AI4Bharat builds open-source translation models for Indic languages, supporting dozens of Indian languages with high accuracy.
| Model | Type | Price | Unit |
|---|---|---|---|
| Indictrans2 En Indic 1B | Translation | $0.342 | per 1M tokens |
Aisingapore
AI Singapore develops regional language models, including the Sea-Lion family tuned for Southeast Asian languages.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma Sea Lion V4 27b It | Text Generation | $0.351 in / $0.555 out | per 1M tokens |
Assemblyai
AssemblyAI provides production-grade speech recognition with speaker diarization and sentiment analysis.
| Model | Type | Price | Unit |
|---|---|---|---|
| Universal 3 Pro | Automatic Speech Recognition | $0.0035 | per audio minute |
Avans06
Avans06 provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Meta Llama 3.2 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Baseten
Baseten provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3.2 3B Instruct Pythonic | Text Generation | $0.044 in / $0.176 out | per 1M tokens |
Braindao
Braindao provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Uncensored | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Deepseek
Deepseek provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| DeepSeek V4 Pro | Text Generation | $1.74 in / $3.48 out | per 1M tokens |
Dima806
Dima806 provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Fairface_age_image_detection | Image Classification | $0.0040 | per image |
Grimjim
Grimjim provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Abliterated | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Haoranxu
Haoranxu provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3 Instruct 8B SimPO | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Hfl
Hfl provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3 Chinese 8b Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Ibm granite
IBM’s Granite models are enterprise-tuned for reliability, safety, and structured business workflows.
| Model | Type | Price | Unit |
|---|---|---|---|
| Granite 4.0 H Micro | Text Generation | $0.017 in / $0.112 out | per 1M tokens |
Khoa klaytn
Khoa klaytn provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bge Base En V1.5 Angle | Text Embeddings | $0.010 | per 1M input tokens |
Kuotient
Kuotient provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Meta Llama 3 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Llava hf
Llava hf provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llava 1.5 7b Hf | Image To Text | $0.050 | per 1M tokens |
Lykon
Lykon provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Dreamshaper 8 Lcm | Text To Image | $0.035 | per image |
M8than
M8than provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Lenientchatfix | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Michaelfeil
Michaelfeil provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bge Small En V1.5 | Text Embeddings | $0.0055 | per 1M input tokens |
Myshell ai
MyShell develops MeloTTS — multilingual text-to-speech with natural prosody.
| Model | Type | Price | Unit |
|---|---|---|---|
| Melotts | Text To Speech | $0.0002 | per 1M input tokens |
P e w
P e w provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Gemma 3 12b It Heretic | Text Generation | $0.080 in / $0.320 out | per 1M tokens |
Pfnet
Preferred Networks develops Plamo — Japanese-tuned embedding models.
| Model | Type | Price | Unit |
|---|---|---|---|
| Plamo Embedding 1b | Text Embeddings | $0.019 | per 1M input tokens |
Philschmid
Philschmid provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Bart Large Cnn Samsum | Text Generation | $0.140 in / $0.560 out | per 1M tokens |
Pipecat ai
Pipecat provides Smart Turn — voice activity detection for conversational AI pipelines.
| Model | Type | Price | Unit |
|---|---|---|---|
| Smart Turn V2 | Voice Activity Detection | $0.0003 | per audio minute |
Pixelcut
Pixelcut provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Pixelcut Background Remover | Image To Image | $0.0013 | per compute second |
Resemble ai
Resemble ai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Chatterboxhd | Text To Speech | $0.0013 | per compute second |
Smoretalk ai
Smoretalk ai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Rembg Enhance (Remove Background Enhance) | Image To Image | $0.0060 | per image |
Speechbrain
Speechbrain provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Lang Id Voxlingua107 Ecapa | Automatic Speech Recognition | $0.050 | per 1M tokens |
Stabilityai
Stabilityai provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Stable Diffusion Xl Base 1.0 | Text To Image | $0.035 | per image |
Unum
Unum develops efficient embedding models for production retrieval systems.
| Model | Type | Price | Unit |
|---|---|---|---|
| UForm Gen2 Qwen 500M | Image To Text | $0.050 | per 1M tokens |
Yentinglin
Yentinglin provides AI models accessible through Greatrouter.
| Model | Type | Price | Unit |
|---|---|---|---|
| Llama 3 Taiwan 8B Instruct | Text Generation | $0.080 in / $0.320 out | per 1M tokens |