theserverless.dev InferenceList

Models

Showing 1001–1050 of 2,347 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
Gemini 3 Flash Preview AtlasCloud text $0.5/1M $3/1M 200K
Gemini 3 Flash Preview Developer AtlasCloud text $0.5/1M $3/1M 200K
Gemini 3.1 Flash Image AtlasCloud text $0.5/1M $3/1M 131K
gemini-3-flash-preview Inference.net text image $0.5/1M $3/1M 1.0M
Google: Gemini 3 Flash Preview Google text image audio video $0.5/1M $3/1M 1.0M
Google: Gemini 3.8 Flash Lite TTS Google text audio $0.5/1M $6/1M 33K
Google: Gemini 3.8 Flash TTS
Cheaper on fal (−98.3%)
 Google text audio $0.5/1M $9/1M 33K
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) Google image text $0.5/1M $3/1M 66K
Google: Nano Banana 2 (Gemini 3.1 Flash Image) Google image text $0.5/1M $3/1M 131K
Kimi K2.5 Fp4 Together text $0.5/1M $2.8/1M 262K
Magistral Small 1.2 Amazon Bedrock text $0.5/1M $1.5/1M —
Magistral Small 1.2 Amazon Bedrock text $0.5/1M $1.5/1M —
Mistral Large 3 Amazon Bedrock text $0.5/1M $1.5/1M —
Mistral Large 3 Amazon Bedrock text $0.5/1M $1.5/1M —
Mistral: Mistral Large 3 2512 Mistral AI text image $0.5/1M $1.5/1M 262K
MoonshotAI: Kimi K2.5
Cheaper on Amazon Bedrock (−40%)
 Moonshot AI text image $0.5/1M $2.5/1M 262K
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B DeepInfra text $0.5/1M $2.2/1M 262K
OpenAI: GPT-6.1 Terra (batch) OpenAI text image $0.5/1M $2.5/1M 1.1M
OpenAI: GPT-6.1 Terra Pro (batch) OpenAI text image $0.5/1M $2.5/1M 1.1M
qwen-3-7-plus Venice text $0.5/1M $2/1M 1M
Qwen3 Coder Next Amazon Bedrock text $0.5/1M $1.2/1M —
Qwen3 Coder Next Fp8 Together text $0.5/1M $1.2/1M 262K
Qwen3-VL-32B-Instruct Together text $0.5/1M $1.5/1M 262K
qwen3.5-397b-a17b NEAR AI text $0.5/1M $3.3/1M 128K
Qwen3.6 Plus Together text $0.5/1M $3/1M 1M
Qwen3.8 27B AtlasCloud text image video $0.5/1M $3/1M 1.0M
Qwen: Qwen3.5 397B A17B Alibaba text image video $0.5/1M $3.6/1M 262K
TitanText-Premier Amazon Bedrock text $0.5/1M $1.5/1M —
venice-uncensored-role-play Venice text $0.5/1M $2/1M 128K
Z.ai: GLM 4.6
Cheaper on DeepInfra (−30%)
 Z.ai text $0.5/1M $2/1M 205K
zai-org/GLM-4.6 DeepInfra text $0.5/1M $2/1M 203K
DeepSeek: R1 0528 Io Net text $0.5237/1M $2.205/1M 128K
Z.ai: GLM 4.7 Io Net text $0.5281/1M $2.072/1M 203K
deepseek-v4-flash-0731 Inference.net text $0.53/1M $1.58/1M 1.0M
Qwen3 VL 235B A22B Amazon Bedrock text $0.53/1M $2.66/1M —
Qwen3 VL 235B A22B Amazon Bedrock text $0.53/1M $2.66/1M —
MoonshotAI: Kimi K2.5 Io Net text image $0.5384/1M $2.835/1M 262K
Z.ai: GLM 4.7
Cheaper on DeepInfra (−41%)
 Z.ai text $0.54/1M $1.98/1M 205K
GLM 4.6 Novita text $0.55/1M $2.2/1M 205K
MiniMax M1 Novita text $0.55/1M $2.2/1M 1M
MiniMax: MiniMax M1 MiniMax text $0.55/1M $2.2/1M 1M
OpenAI: o3 Mini (batch) OpenAI text $0.55/1M $2.2/1M 200K
OpenAI: o4 Mini (batch) OpenAI image text $0.55/1M $2.2/1M 200K
Qwen3.5 397BA17B AtlasCloud text image video $0.55/1M $3.5/1M 262K
Qwen: Qwen3.5 397B A17B Phala text image video $0.55/1M $3.5/1M 262K
TheDrummer: Skyfall 36B V2 Thedrummer text $0.55/1M $0.8/1M 33K
zai-org-glm-4.7 Venice text $0.55/1M $2.65/1M 198K
@cf/meta/llama-2-7b-chat-fp16 Cloudflare text $0.556/1M $6.667/1M —
kimi-k2-5 Venice text $0.56/1M $3.5/1M 256K
MoonshotAI: Kimi K2.7 Code
Cheaper on Inceptron (−30.2%)
 Moonshot AI text image $0.56/1M $3.1/1M 262K

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