theserverless.dev InferenceList

Models

Showing 701–750 of 2,347 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
openai-gpt-56-luna-pro Venice text $0.2/1M $1.2/1M 1M
openai/gpt-oss-120b-Ultra DeepInfra text $0.2/1M $0.95/1M 131K
OpenAI: GPT-4.1 Mini (batch) OpenAI image text $0.2/1M $0.8/1M 1.0M
OpenAI: GPT-5.4 Nano OpenAI text image $0.2/1M $1.25/1M 400K
OpenAI: GPT-5.6 Luna OpenAI text image $0.2/1M $1.2/1M 1.1M
OpenAI: GPT-5.6 Luna Phala text image $0.2/1M $1.2/1M 272K
OpenAI: GPT-5.6 Luna Pro OpenAI text image $0.2/1M $1.2/1M 1.1M
Qwen/Qwen3-VL-235B-A22B-Instruct DeepInfra text image $0.2/1M $0.88/1M 262K
Qwen/Qwen3.8-27B DeepInfra text image $0.2/1M $2.5/1M 262K
Qwen3 VL 30B A3B Instruct Novita text video image $0.2/1M $0.7/1M 131K
Qwen: Qwen3 VL 30B A3B Instruct Phala text image $0.2/1M $0.7/1M 128K
Qwen: Qwen3.6 35B A3B Phala text image video $0.2/1M $1.27/1M 262K
Qwen: Qwen3.8 27B Phala text image video $0.2/1M $2.5/1M 1M
Step 3.7 Flash Novita text image video $0.2/1M $1.15/1M 262K
StepFun: Step 3.7 Flash Stepfun text image video $0.2/1M $1.15/1M 262K
TitanTextG1-Express Amazon Bedrock text $0.2/1M $0.6/1M —
venice-uncensored-1-2 Venice text $0.2/1M $0.9/1M 128K
Venice: Uncensored Cognitivecomputations text $0.2/1M $0.9/1M 128K
Voxtral Small 24B Tinfoil text $0.2/1M $0.6/1M 33K
xAI: Grok 4.1 Fast Phala text image $0.2/1M $0.5/1M 2M
xAI: Grok Code Fast 1 Phala text $0.2/1M $1.5/1M 256K
@cf/baai/bge-large-en-v1.5 Cloudflare text $0.204/1M Not published— —
qwen3-vl-235b-a22b Venice text $0.21/1M $1.9/1M 128K
Qwen: Qwen3 VL 235B A22B Instruct
Cheaper on DeepInfra (−41.5%)
 Alibaba text image $0.21/1M $1.9/1M 262K
DeepSeek: DeepSeek V4 Flash Vision Exp DeepSeek text image $0.2156/1M $0.6468/1M 1.0M
gpt-oss-120b SambaNova text $0.22/1M $0.59/1M 131K
Llama 3.1 8B Amazon Bedrock text $0.22/1M $0.22/1M —
Qwen3 235B A22B 2507 Amazon Bedrock text $0.22/1M $0.88/1M —
Xing4.0-29B-A4B Phala text $0.22/1M $0.9/1M 262K
Qwen3.5 35B A3B AtlasCloud text image video $0.225/1M $1.8/1M 262K
qwen3-14b Inference.net text $0.2275/1M $0.91/1M 131K
deepseek-v4-flash Inference.net text $0.23/1M $0.62/1M 1M
Gemma 3 27B Amazon Bedrock text $0.23/1M $0.38/1M —
Gemma 3 27B Amazon Bedrock text $0.23/1M $0.38/1M —
Qwen: Qwen3.7 Plus (batch) Alibaba text image $0.23/1M $0.92/1M 262K
@cf/cloudflare/clef Cloudflare text $0.24/1M Not published— —
Cloudflare: Clef
Cheaper on DeepInfra (−20%)
 Cloudflare text image $0.24/1M $0/1M 66K
Llama 4 Maverick 17B Amazon Bedrock text $0.24/1M $0.97/1M —
Macaron V1 Tall Novita text $0.2475/1M $1.43/1M 262K
Qwen3.6 35B A3B Novita text image video $0.248/1M $1.485/1M 262K
ByteDance Seed: Seed 1.6 ByteDance image text video $0.25/1M $2/1M 262K
ByteDance Seed: Seed-2.0-Lite ByteDance text image video $0.25/1M $2/1M 262K
ByteDance/Seed-1.8 DeepInfra text image $0.25/1M $2/1M 256K
Claude 3 Haiku Amazon Bedrock text $0.25/1M Not published— —
deepseek-ai/DeepSeek-V3.1 DeepInfra text $0.25/1M $0.95/1M 164K
DeepSeek: DeepSeek V3.1 DeepSeek text $0.25/1M $0.95/1M 164K
Doubao Seed 1.6 AtlasCloud text $0.25/1M $2/1M 262K
Doubao Seed 1.8 AtlasCloud text $0.25/1M $2/1M 262K
Doubao Seed 2.0 Lite AtlasCloud text $0.25/1M $2/1M 262K
e2ee-qwen3-vl-30b-a3b-p Venice text $0.25/1M $0.9/1M 128K

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