theserverless.dev InferenceList

Models

Showing 651–700 of 2,347 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
Llama 4 Scout Instruct (17Bx16E) Together text $0.18/1M $0.59/1M 1.0M
Meta Llama 3.1 8B Instruct Turbo Together text $0.18/1M $0.18/1M 131K
meta-llama/Llama-Guard-4-12B DeepInfra text image $0.18/1M $0.18/1M 164K
Meta: Llama Guard 4 12B
Cheaper on DeepInfra (−20%)
 Meta image text $0.18/1M $0.18/1M 164K
Qwen3-VL-8B-Instruct Together text $0.18/1M $0.68/1M 262K
Tencent: Hy3 preview Tencent text $0.18/1M $0.6/1M 262K
e2ee-deepseek-v4-flash Venice text $0.182/1M $0.373/1M 1M
e2ee-qwen3-6-35b-a3b Venice text $0.182/1M $1.18/1M 32K
Qwen3.6 35B A3B AtlasCloud text image video $0.186/1M $1.114/1M 262K
Meta: Llama 4 Maverick Meta text image $0.1875/1M $0.6525/1M 524K
minimax-m3-1-flash Venice text $0.1875/1M $0.75/1M 1M
Qwen: Qwen3.6 Flash Alibaba text image video $0.1875/1M $1.125/1M 1M
e2ee-gemma-4-26b-a4b-uncensored-p Venice text $0.19/1M $0.88/1M 64K
MoonshotAI: Kimi K3
Cheaper on Inference.net (−65%)
 Moonshot AI text image video $0.192/1M $15/1M 1.0M
Qwen: Qwen3 Coder Flash Alibaba text $0.195/1M $0.975/1M 1M
@cf/openai/gpt-oss-20b Cloudflare text $0.2/1M $0.3/1M —
deepseek-ai/DeepSeek-V4.1-Flash DeepInfra text image $0.2/1M $0.6/1M 1.0M
deepseek-ai/DeepSeek-V4.1-Flash-1017 DeepInfra text image $0.2/1M $0.6/1M 1.0M
Doubao Seed Character AtlasCloud text image video $0.2/1M $0.8/1M 131K
Glm 4.5 Air Fp8 Together text $0.2/1M $1.1/1M 131K
google/gemma-4-31B-it DeepInfra text image $0.2/1M $0.4/1M 262K
Google: Gemini Embedding 2 Google text image audio video $0.2/1M $0/1M 8K
Google: Gemini Embedding 2 Preview Google text image audio video $0.2/1M $0/1M 8K
Google: Gemma 4 31B
Cheaper on CoreWeave (−36%)
 Google image text video $0.2/1M $0.4/1M 262K
gpt 4.1 mini Batch Outp glbl Azure text $0.2/1M $0.8/1M —
GPT 5.6 Luna AtlasCloud text image $0.2/1M $1.2/1M 1.1M
GPT 5.6 Luna AtlasCloud text image $0.2/1M $1.2/1M 1.1M
GPT-5.4 Nano NEAR AI text $0.2/1M $1.25/1M 400K
GPT-5.6 Luna NEAR AI text image $0.2/1M $1.2/1M 1.1M
gpt-5.6-luna Inference.net text image $0.2/1M $1.2/1M 1.1M
Hunyuan 3 AtlasCloud text $0.2/1M $0.8/1M 262K
Meta Llama 3 8B Instruct Together text $0.2/1M $0.2/1M 8K
Meta Llama 3 8B Instruct Reference Together text $0.2/1M $0.2/1M 8K
Meta Llama 3.1 8B Together text $0.2/1M $0.2/1M 16K
MiniMax: MiniMax-01 MiniMax text image $0.2/1M $1.1/1M 1.0M
Ministral 14B 3.0 Amazon Bedrock text $0.2/1M $0.2/1M —
Ministral 14B 3.0 Amazon Bedrock text $0.2/1M $0.2/1M —
Ministral 3 14B Instruct 2512 Together text $0.2/1M $0.2/1M 262K
Mistral (7B) Instruct v0.1 Together text $0.2/1M $0.2/1M 33K
Mistral (7B) Instruct v0.3 Together text $0.2/1M $0.2/1M 33K
Mistral: Ministral 3 14B 2512 Mistral AI text image $0.2/1M $0.2/1M 262K
Mistral: Saba Mistral AI text $0.2/1M $0.6/1M 33K
Nova Pro Amazon Bedrock text $0.2/tokens cache read Not published— —
Nova Pro Amazon Bedrock text $0.2/tokens cache read Not published— —
NVIDIA Nemotron Nano 2 VL Amazon Bedrock text $0.2/1M $0.6/1M —
NVIDIA Nemotron Nano 2 VL Amazon Bedrock text $0.2/1M $0.6/1M —
nvidia-nemotron-3-5-super-vl-120b-a12b Venice text $0.2/1M $0.5/1M 262K
nvidia/Nemotron-Content-Safety-3.5 DeepInfra text image $0.2/1M $0.2/1M 131K
NVIDIA: Nemotron 3.5 Content Safety NVIDIA text image $0.2/1M $0.2/1M 131K
openai-gpt-56-luna Venice text $0.2/1M $1.2/1M 1M

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