theserverless.dev InferenceList

Models

Showing 1–50 of 116 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
DeepInfra × Clear
Model Provider Modality Input ↑ Output Context
google/embeddinggemma-300m DeepInfra text $0.002/1M Not published— 2K
BAAI/bge-base-en-v1.5 DeepInfra text $0.005/1M Not published— 512
intfloat/e5-base-v2 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/all-MiniLM-L12-v2 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/all-MiniLM-L6-v2 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/all-mpnet-base-v2 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/clip-ViT-B-32 DeepInfra text $0.005/1M Not published— 77
sentence-transformers/clip-ViT-B-32-multilingual-v1 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/multi-qa-mpnet-base-dot-v1 DeepInfra text $0.005/1M Not published— 512
sentence-transformers/paraphrase-MiniLM-L6-v2 DeepInfra text $0.005/1M Not published— 512
shibing624/text2vec-base-chinese DeepInfra text $0.005/1M Not published— 512
thenlper/gte-base DeepInfra text $0.005/1M Not published— 512
BAAI/bge-en-icl DeepInfra text $0.01/1M Not published— 8K
BAAI/bge-large-en-v1.5 DeepInfra text $0.01/1M Not published— 512
BAAI/bge-m3 DeepInfra text $0.01/1M Not published— 8K
BAAI/bge-m3-multi DeepInfra text $0.01/1M Not published— 512
BAAI/bge-m3-multi-8k DeepInfra text $0.01/1M Not published— 8K
intfloat/e5-large-v2 DeepInfra text $0.01/1M Not published— 512
intfloat/multilingual-e5-large DeepInfra text $0.01/1M Not published— 512
intfloat/multilingual-e5-large-instruct DeepInfra text $0.01/1M Not published— 512
nvidia/llama-nemotron-embed-vl-1b-v2 DeepInfra text $0.01/1M Not published— 10K
Qwen/Qwen3-Embedding-0.6B DeepInfra text $0.01/1M Not published— 33K
Qwen/Qwen3-Embedding-8B DeepInfra text $0.01/1M Not published— 33K
thenlper/gte-large DeepInfra text $0.01/1M Not published— 512
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo DeepInfra text $0.02/1M $0.04/1M 131K
Qwen/Qwen3-Embedding-4B DeepInfra text $0.02/1M Not published— 33K
mistralai/Mistral-Nemo-Instruct-2407 DeepInfra text $0.029/1M $0.03/1M 131K
openai/gpt-oss-20b DeepInfra text $0.03/1M $0.14/1M 131K
openai/gpt-oss-120b DeepInfra text $0.037/1M $0.17/1M 131K
Sao10K/L3-8B-Lunaris-v1-Turbo DeepInfra text $0.04/1M $0.05/1M 8K
google/gemma-3-12b-it DeepInfra text image $0.05/1M $0.15/1M 131K
google/gemma-3-4b-it DeepInfra text image $0.05/1M $0.1/1M 131K
mistralai/Mistral-Small-24B-Instruct-2501 DeepInfra text $0.05/1M $0.08/1M 33K
deepseek-ai/DeepSeek-V4-Flash-0731 DeepInfra text $0.06/1M $0.18/1M 1.0M
ibm-granite/granite-4.2-8b DeepInfra text $0.06/1M $0.25/1M 131K
inclusionAI/Ling-3.0-flash DeepInfra text $0.06/1M $0.18/1M 131K
inclusionAI/Ling-3.0-flash-VL DeepInfra text image $0.06/1M $0.18/1M 131K
nvidia/NVIDIA-Nemotron-3.5-Lightning DeepInfra text $0.06/1M $0.16/1M 262K
google/gemma-4-26B-A4B-it DeepInfra text image $0.07/1M $0.34/1M 262K
microsoft/phi-4 DeepInfra text $0.07/1M $0.14/1M 16K
mistralai/Mistral-Small-3.2-24B-Instruct-2506 DeepInfra text image $0.075/1M $0.2/1M 128K
google/gemma-3-27b-it DeepInfra text image $0.08/1M $0.16/1M 131K
Qwen/Qwen3-32B DeepInfra text $0.08/1M $0.28/1M 41K
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B DeepInfra text $0.085/1M $0.4/1M 262K
deepseek-ai/DeepSeek-V4-Flash DeepInfra text $0.09/1M $0.18/1M 1.0M
google/gemma-4-31B-it-turbo DeepInfra text image $0.09/1M $0.34/1M 262K
Qwen/Qwen3-235B-A22B-Instruct-2507 DeepInfra text $0.09/1M $0.55/1M 262K
Qwen/Qwen3-Next-80B-A3B-Instruct DeepInfra text $0.09/1M $1.1/1M 262K
ByteDance/Seed-2.0-mini DeepInfra text image $0.1/1M $0.4/1M 256K
meta-llama/Llama-3.3-70B-Instruct-Turbo DeepInfra text $0.1/1M $0.32/1M 131K

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.