DeepInfra
DeepInfra (deepinfra, Inference host, headquartered in US) serves 115 models through the Autonomous Relay Agents API. Prices are the provider's list prices, per million tokens.
| Model | Model id | Context | Input | Output |
|---|---|---|---|---|
| Audio8/Audio8-TTS-Preview-0.6b | Audio8/Audio8-TTS-Preview-0.6b | — | — | — |
| BAAI/bge-base-en-v1.5 | BAAI/bge-base-en-v1.5 | 512 | $0.005 per M | — |
| BAAI/bge-en-icl | BAAI/bge-en-icl | 8,192 | $0.01 per M | — |
| BAAI/bge-large-en-v1.5 | BAAI/bge-large-en-v1.5 | 512 | $0.01 per M | — |
| BAAI/bge-m3 | BAAI/bge-m3 | 8,192 | $0.01 per M | — |
| BAAI/bge-m3-multi | BAAI/bge-m3-multi | 512 | $0.01 per M | — |
| BAAI/bge-m3-multi-8k | BAAI/bge-m3-multi-8k | 8,192 | $0.01 per M | — |
| Bria/Bria-3.2 | Bria/Bria-3.2 | — | — | — |
| Bria/Bria-3.2-vector | Bria/Bria-3.2-vector | — | — | — |
| Bria/blur_background | Bria/blur_background | — | — | — |
| Bria/erase_foreground | Bria/erase_foreground | — | — | — |
| Bria/expand | Bria/expand | — | — | — |
| Bria/fibo | Bria/fibo | — | — | — |
| Bria/fibo_edit | Bria/fibo_edit | — | — | — |
| Bria/remove_background | Bria/remove_background | — | — | — |
| ByteDance/Seed-1.8 | ByteDance/Seed-1.8 | 256,000 | $0.25 per M | $2.00 per M |
| ByteDance/Seed-2.0-pro | ByteDance/Seed-2.0-pro | 256,000 | $0.50 per M | $3.00 per M |
| ByteDance/Seedance-1.5-Pro | ByteDance/Seedance-1.5-Pro | — | — | — |
| ByteDance/Seedance-2.0 | ByteDance/Seedance-2.0 | — | — | — |
| ByteDance/Seedream-4 | ByteDance/Seedream-4 | — | — | — |
| MiniMaxAI/MiniMax-M2.7-Turbo | MiniMaxAI/MiniMax-M2.7-Turbo | 196,608 | $0.38 per M | $1.70 per M |
| Pixverse/Pixverse-6-T2V | Pixverse/Pixverse-6-T2V | — | — | — |
| Pixverse/Pixverse-T2V | Pixverse/Pixverse-T2V | — | — | — |
| Pixverse/Pixverse-T2V-HD | Pixverse/Pixverse-T2V-HD | — | — | — |
| PrunaAI/p-image | PrunaAI/p-image | — | — | — |
| PrunaAI/p-video | PrunaAI/p-video | — | — | — |
| Qwen/Qwen-Image-Edit | Qwen/Qwen-Image-Edit | — | — | — |
| Qwen/Qwen-Image-Max | Qwen/Qwen-Image-Max | — | — | — |
| Qwen/Qwen3-235B-A22B-Instruct-2507 | Qwen/Qwen3-235B-A22B-Instruct-2507 | 262,144 | $0.09 per M | $0.55 per M |
| Qwen/Qwen3-ASR-0.6B | Qwen/Qwen3-ASR-0.6B | — | — | — |
| Qwen/Qwen3-ASR-1.7B | Qwen/Qwen3-ASR-1.7B | — | — | — |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | 262,144 | $0.30 per M | $1.00 per M |
| Qwen/Qwen3-Embedding-0.6B | Qwen/Qwen3-Embedding-0.6B | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Embedding-4B | Qwen/Qwen3-Embedding-4B | 32,768 | $0.02 per M | — |
| Qwen/Qwen3-Embedding-8B | Qwen/Qwen3-Embedding-8B | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Reranker-0.6B | Qwen/Qwen3-Reranker-0.6B | 32,768 | $0.01 per M | — |
| Qwen/Qwen3-Reranker-4B | Qwen/Qwen3-Reranker-4B | 32,768 | $0.025 per M | — |
| Qwen/Qwen3-Reranker-8B | Qwen/Qwen3-Reranker-8B | 32,768 | $0.05 per M | — |
| Qwen/Qwen3-TTS | Qwen/Qwen3-TTS | — | — | — |
| Qwen/Qwen3-TTS-VoiceDesign | Qwen/Qwen3-TTS-VoiceDesign | — | — | — |
| Qwen/Qwen3.8-Max | Qwen/Qwen3.8-Max | 256,000 | $1.65 per M | $4.95 per M |
| ResembleAI/chatterbox-multilingual | ResembleAI/chatterbox-multilingual | — | — | — |
| ResembleAI/chatterbox-turbo | ResembleAI/chatterbox-turbo | — | — | — |
| Sao10K/L3-8B-Lunaris-v1-Turbo | Sao10K/L3-8B-Lunaris-v1-Turbo | 8,192 | $0.04 per M | $0.05 per M |
| Sao10K/L3.1-70B-Euryale-v2.2 | Sao10K/L3.1-70B-Euryale-v2.2 | 131,072 | $0.85 per M | $0.85 per M |
| Wan-AI/Wan2.2-T2V-A14B | Wan-AI/Wan2.2-T2V-A14B | — | — | — |
| Wan-AI/Wan2.6-T2I | Wan-AI/Wan2.6-T2I | — | — | — |
| Wan-AI/Wan2.6-T2V | Wan-AI/Wan2.6-T2V | — | — | — |
| XiaomiMiMo/MiMo-V2.5-tts | XiaomiMiMo/MiMo-V2.5-tts | — | — | — |
| XiaomiMiMo/MiMo-V2.5-tts-voicedesign | XiaomiMiMo/MiMo-V2.5-tts-voicedesign | — | — | — |
| black-forest-labs/FLUX-1-Redux-dev | black-forest-labs/FLUX-1-Redux-dev | — | — | — |
| black-forest-labs/FLUX-1-dev | black-forest-labs/FLUX-1-dev | — | — | — |
| black-forest-labs/FLUX-1-schnell | black-forest-labs/FLUX-1-schnell | — | — | — |
| black-forest-labs/FLUX-1.1-pro | black-forest-labs/FLUX-1.1-pro | — | — | — |
| black-forest-labs/FLUX-2-dev | black-forest-labs/FLUX-2-dev | — | — | — |
| black-forest-labs/FLUX-2-klein-4b | black-forest-labs/FLUX-2-klein-4b | — | — | — |
| black-forest-labs/FLUX-2-klein-9b | black-forest-labs/FLUX-2-klein-9b | — | — | — |
| black-forest-labs/FLUX-2-max | black-forest-labs/FLUX-2-max | — | — | — |
| black-forest-labs/FLUX-2-pro | black-forest-labs/FLUX-2-pro | — | — | — |
| black-forest-labs/FLUX.1-Kontext-dev | black-forest-labs/FLUX.1-Kontext-dev | — | — | — |
| bosonai/HiggsAudioV2.5 | bosonai/HiggsAudioV2.5 | — | — | — |
| deepseek-ai/DeepSeek-V3 | deepseek-ai/DeepSeek-V3 | 163,840 | $0.32 per M | $0.89 per M |
| deepseek-ai/DeepSeek-V3-0324 | deepseek-ai/DeepSeek-V3-0324 | 163,840 | $0.24 per M | $0.90 per M |
| deepseek-ai/DeepSeek-V3.1 | deepseek-ai/DeepSeek-V3.1 | 163,840 | $0.25 per M | $0.95 per M |
| google/embeddinggemma-300m | google/embeddinggemma-300m | 2,048 | $0.002 per M | — |
| google/gemini-3.1-pro | google/gemini-3.1-pro | 1,000,000 | $2.00 per M | $12.00 per M |
| google/gemma-4-31B-it-Ultra | google/gemma-4-31B-it-Ultra | 131,072 | $0.27 per M | $0.76 per M |
| google/gemma-4-31B-it-turbo | google/gemma-4-31B-it-turbo | 262,144 | $0.09 per M | $0.34 per M |
| google/gemma-4-E4B-it | google/gemma-4-E4B-it | 131,072 | $0.02 per M | $0.10 per M |
| google/nano-banana-2 | google/nano-banana-2 | — | — | — |
| google/nano-banana-2-lite | google/nano-banana-2-lite | — | — | — |
| google/nano-banana-pro | google/nano-banana-pro | — | — | — |
| google/veo-3.1 | google/veo-3.1 | — | — | — |
| google/veo-3.1-fast | google/veo-3.1-fast | — | — | — |
| hexgrad/Kokoro-82M | hexgrad/Kokoro-82M | — | — | — |
| ibm-granite/granite-4.2-30b | ibm-granite/granite-4.2-30b | 131,072 | $0.16 per M | $0.65 per M |
| ibm-granite/granite-4.2-3b | ibm-granite/granite-4.2-3b | 131,072 | $0.03 per M | $0.12 per M |
| intfloat/e5-base-v2 | intfloat/e5-base-v2 | 512 | $0.005 per M | — |
| intfloat/e5-large-v2 | intfloat/e5-large-v2 | 512 | $0.01 per M | — |
| intfloat/multilingual-e5-large | intfloat/multilingual-e5-large | 512 | $0.01 per M | — |
| intfloat/multilingual-e5-large-instruct | intfloat/multilingual-e5-large-instruct | 512 | $0.01 per M | — |
| inworld-ai/realtime-tts-1.5-max | inworld-ai/realtime-tts-1.5-max | — | — | — |
| inworld-ai/realtime-tts-1.5-mini | inworld-ai/realtime-tts-1.5-mini | — | — | — |
| inworld-ai/realtime-tts-2 | inworld-ai/realtime-tts-2 | — | — | — |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | meta-llama/Llama-3.3-70B-Instruct-Turbo | 131,072 | $0.10 per M | $0.32 per M |
| meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | 1,048,576 | $0.20 per M | $0.80 per M |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | meta-llama/Llama-4-Scout-17B-16E-Instruct | 327,680 | $0.10 per M | $0.30 per M |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | 131,072 | $0.40 per M | $0.40 per M |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | 131,072 | $0.02 per M | $0.04 per M |
| mistralai/Mistral-Nemo-Instruct-2407 | mistralai/Mistral-Nemo-Instruct-2407 | 131,072 | $0.019 per M | $0.03 per M |
| mistralai/Mistral-Small-3.2-24B-Instruct-2506 | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | 128,000 | $0.075 per M | $0.20 per M |
| mistralai/Voxtral-Mini-3B-2507 | mistralai/Voxtral-Mini-3B-2507 | — | — | — |
| nvidia/Cosmos3-Nano | nvidia/Cosmos3-Nano | — | — | — |
| nvidia/Cosmos3-Super | nvidia/Cosmos3-Super | — | — | — |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | 262,144 | $0.085 per M | $0.40 per M |
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | 262,144 | $0.50 per M | $2.20 per M |
| nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b | nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b | — | — | — |
| nvidia/Nemotron-Content-Safety-3.5 | nvidia/Nemotron-Content-Safety-3.5 | 131,072 | $0.20 per M | $0.20 per M |
| nvidia/llama-nemotron-embed-vl-1b-v2 | nvidia/llama-nemotron-embed-vl-1b-v2 | 10,240 | $0.01 per M | — |
| openai/gpt-oss-120b-Turbo | openai/gpt-oss-120b-Turbo | 131,072 | $0.15 per M | $0.60 per M |
| openai/gpt-oss-120b-Ultra | openai/gpt-oss-120b-Ultra | 131,072 | $0.20 per M | $0.95 per M |
| openai/whisper-large-v3 | openai/whisper-large-v3 | — | — | — |
| openai/whisper-large-v3-turbo | openai/whisper-large-v3-turbo | — | — | — |
| sentence-transformers/all-MiniLM-L12-v2 | sentence-transformers/all-MiniLM-L12-v2 | 512 | $0.005 per M | — |
| sentence-transformers/all-MiniLM-L6-v2 | sentence-transformers/all-MiniLM-L6-v2 | 512 | $0.005 per M | — |
| sentence-transformers/all-mpnet-base-v2 | sentence-transformers/all-mpnet-base-v2 | 512 | $0.005 per M | — |
| sentence-transformers/clip-ViT-B-32 | sentence-transformers/clip-ViT-B-32 | 77 | $0.005 per M | — |
| sentence-transformers/clip-ViT-B-32-multilingual-v1 | sentence-transformers/clip-ViT-B-32-multilingual-v1 | 512 | $0.005 per M | — |
| sentence-transformers/multi-qa-mpnet-base-dot-v1 | sentence-transformers/multi-qa-mpnet-base-dot-v1 | 512 | $0.005 per M | — |
| sentence-transformers/paraphrase-MiniLM-L6-v2 | sentence-transformers/paraphrase-MiniLM-L6-v2 | 512 | $0.005 per M | — |
| sesame/csm-1b | sesame/csm-1b | — | — | — |
| shibing624/text2vec-base-chinese | shibing624/text2vec-base-chinese | 512 | $0.005 per M | — |
| stabilityai/sdxl-turbo | stabilityai/sdxl-turbo | — | — | — |
| thenlper/gte-base | thenlper/gte-base | 512 | $0.005 per M | — |
| thenlper/gte-large | thenlper/gte-large | 512 | $0.01 per M | — |