theserverless.dev InferenceList

Models

Showing 951–1000 of 1,880 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
Elorian: Glimpse Elorian text image video $0.6/1M $3/1M 262K
GLM 4.5V Novita text video image $0.6/1M $1.8/1M 66K
GLM 4.6 Fp8 Together text $0.6/1M $2.2/1M 203K
GLM 4.7 Amazon Bedrock text $0.6/1M $2.2/1M —
GLM 4.7 Novita text $0.6/1M $2.2/1M 205K
GLM 4.7 Novita text $0.6/1M $2.2/1M 205K
Kimi K2 Instruct 0905 Novita text $0.6/1M $2.5/1M 262K
Kimi K2 Thinking Amazon Bedrock text $0.6/1M $2.5/1M —
Kimi K2 Thinking Amazon Bedrock text $0.6/1M $2.5/1M —
Kimi K2 Thinking Novita text $0.6/1M $2.5/1M 262K
Kimi K2.5 Amazon Bedrock text $0.6/1M $3/1M —
Kimi K2.5 Novita text image video $0.6/1M $3/1M 262K
Meta-Llama-3.3-70B-Instruct SambaNova text $0.6/1M $1.2/1M 131K
MiniMax M2.7-highspeed Novita text $0.6/1M $2.4/1M 205K
Mixtral-8x7B Instruct v0.1 Together text $0.6/1M $0.6/1M 33K
MoonshotAI: Kimi K2 0905 Moonshot AI text $0.6/1M $2.5/1M 262K
MoonshotAI: Kimi K2 Thinking Io Net text $0.6/1M $2.5/1M 262K
MoonshotAI: Kimi K2 Thinking
Cheaper on Amazon Bedrock (−50%)
 Moonshot AI text $0.6/1M $2.5/1M 262K
Nous Hermes 2 Mixtral 8X7B Dpo Together text $0.6/1M $0.6/1M 33K
NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 Together text $0.6/1M $3.6/1M 512K
NVIDIA: Nemotron 3 Ultra
Cheaper on DeepInfra (−29.5%)
 NVIDIA text $0.6/1M $2.4/1M 262K
OpenAI: GPT Audio Mini OpenAI text audio $0.6/1M $2.4/1M 128K
Qwen3.5 397B A17B Novita text image video $0.6/1M $3.6/1M 262K
Qwen3.5 397B A17b Together text $0.6/1M $3.6/1M 262K
Qwen3.6 27B Novita text image video $0.6/1M $3.6/1M 262K
Writer: Palmyra X5 Writer text $0.6/1M $6/1M 1.0M
Z.ai: GLM 4.5 Z.ai text $0.6/1M $2.2/1M 131K
Z.ai: GLM 4.5V Z.ai text image $0.6/1M $1.8/1M 66K
DeepSeek v3.2 Amazon Bedrock text $0.62/1M $1.85/1M —
WizardLM 2 8x22B Novita text $0.62/1M $0.62/1M 66K
Nova Premier Amazon Bedrock text $0.625/tokens cache read Not published— —
nvidia-nemotron-3-ultra-550b-a55b Venice text $0.625/1M $3.125/1M 256K
OpenAI: GPT-5 (batch) OpenAI text image $0.625/1M $5/1M 400K
OpenAI: GPT-5.1 (batch) OpenAI image text $0.625/1M $5/1M 400K
qwen-3-6-plus Venice text $0.625/1M $3.75/1M 1M
seed-2-1-turbo Venice text $0.625/1M $3.125/1M 256K
DeepSeek V4.1 Flash Tinfoil text image $0.65/1M $1.45/1M 1.0M
Google: Gemma 2 27B Google text $0.65/1M $0.65/1M 8K
MoonshotAI: Kimi K2.6
Cheaper on Chutes (−56.6%)
 Moonshot AI text image $0.65/1M $3.41/1M 262K
@cf/qwen/qwen2.5-coder-32b-instruct Cloudflare text $0.66/1M $1/1M —
@cf/qwen/qwq-32b Cloudflare text $0.66/1M $1/1M —
DeepSeek: DeepSeek V4 Pro 0813
Cheaper on Sail Research (−18.6%)
 DeepSeek text $0.66/1M $1.98/1M 1.0M
Qwen2.5 Coder 32B Instruct Alibaba text $0.66/1M $1/1M 33K
AionLabs: Aion 3.5 Mini Aion Labs text $0.7/1M $1.4/1M 262K
AionLabs: Aion-3.0-Mini Aion Labs text $0.7/1M $1.4/1M 131K
DeepSeek R1 0528 Novita text $0.7/1M $2.5/1M 164K
DeepSeek R1 Turbo Novita text $0.7/1M $2.5/1M 64K
deepseek-v3.2 Inference.net text $0.7/1M $2/1M 164K
gemini-3-flash-preview Venice text $0.7/1M $3.75/1M 256K
llama-3.3-70b Venice text $0.7/1M $2.8/1M 128K

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