theserverless.dev InferenceList

Models

Showing 1351–1400 of 1,880 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Model Provider Modality Input ↑ Output Context
OpenAI: GPT-5.6 Terra Pro OpenAI text image $2/1M $12/1M 1.1M
OpenAI: GPT-6 Sol OpenAI text image $2/1M $10/1M 1.1M
OpenAI: GPT-6 Sol Phala text image $2/1M $10/1M 272K
OpenAI: GPT-6 Sol Pro OpenAI text image $2/1M $10/1M 1.1M
OpenAI: GPT-6.1 Sol OpenAI text image $2/1M $10/1M 1.1M
OpenAI: GPT-6.1 Sol Phala text image $2/1M $10/1M 272K
OpenAI: GPT-6.1 Sol Pro OpenAI text image $2/1M $10/1M 1.1M
OpenAI: o3 OpenAI image text $2/1M $8/1M 200K
OpenAI: o3 Phala image text $2/1M $8/1M 200K
Oracle Cloud Infrastructure Generative AI - xAI - Grok 4.7 - Input Tokens Short Context Oracle Cloud text $2/1M $6/1M —
Perplexity: Sonar Deep Research Perplexity text $2/1M $8/1M 128K
Perplexity: Sonar Reasoning Pro Perplexity text image $2/1M $8/1M 128K
Pixtral Large 25.02 Amazon Bedrock text $2/1M $6/1M —
Qwen3 Coder 480B A35B Instruct Fp8 Together text $2/1M $2/1M 262K
Qwen3.8 2.4T A95B Novita text $2/1M $6/1M 1M
Qwen3.8 Max AtlasCloud text image video $2/1M $6/1M 1M
Qwen3.8 Max Novita text image video $2/1M $6/1M 1M
Qwen3.8-2.4T-A95B Together text $2/1M $6/1M 1.0M
Qwen: Qwen3.8 2.4T A95B Alibaba text $2/1M $6/1M 1.0M
Qwen: Qwen3.8 Max (0902) Alibaba text image video $2/1M $6/1M 1M
Sakana: Fugu Max Sakana text image $2/1M $6/1M 1M
SpaceXAI: Grok 4.5 xAI text image $2/1M $6/1M 500K
SpaceXAI: Grok 4.6 xAI text image $2/1M $6/1M 500K
SpaceXAI: Grok 4.7
Cheaper on Amazon Bedrock (−45%)
 xAI text image $2/1M $6/1M 500K
xAI: Grok Latest xAI text image $2/1M $6/1M 500K
deepseek-v4-pro Inference.net text $2.1/1M $4.2/1M 1.0M
Grok 4.7 Amazon Bedrock text $2.2/1M $6.6/1M —
grok-4-5 Venice text $2.27/1M $6.8/1M 500K
grok-4-6 Venice text $2.27/1M $6.8/1M 500K
grok-4-7 Venice text $2.27/1M $6.8/1M 500K
MoonshotAI: Kimi K3 (batch) Moonshot AI text image video $2.28/1M $11.4/1M 1.0M
Meta: Muse Image Meta text image $2.395/1M Not published— 66K
Amazon: Nova Premier 1.0 Amazon text image $2.5/1M $12.5/1M 1M
Anthropic: Claude Opus 4.5 (batch) Anthropic text image $2.5/1M $12.5/1M 200K
Anthropic: Claude Opus 4.6 (batch) Anthropic text image $2.5/1M $12.5/1M 1M
Anthropic: Claude Opus 4.7 (batch) Anthropic text image $2.5/1M $12.5/1M 1M
Anthropic: Claude Opus 4.8 (batch) Anthropic text image $2.5/1M $12.5/1M 1M
Anthropic: Claude Opus 5 (batch) Anthropic text image $2.5/1M $12.5/1M 1M
Cohere: Command A Cohere text $2.5/1M $10/1M 256K
Cohere: Command R+ (08-2024) Cohere text $2.5/1M $10/1M 128K
Command A Outp DZ Azure text $2.5/1M $11/1M —
gemini-3-1-pro-preview Venice text $2.5/1M $15/1M 1M
gemini-4-argon Venice text $2.5/1M $12.5/1M 1M
Google: Gemini 2.5 Pro Phala text image audio video $2.5/1M $15/1M 1.0M
gpt-4o Inference.net text image $2.5/1M $10/1M 128K
gpt-5.4 Inference.net text image $2.5/1M $15/1M 1.1M
GPT-5.4 NEAR AI text $2.5/1M $15/1M 1.1M
Magnum v4 72B Anthracite Org text $2.5/1M $5/1M 33K
Nova Premier Amazon Bedrock text $2.5/1M $12.5/1M —
openai-gpt-4o-2024-11-20 Venice text $2.5/1M $10/1M 128K

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