AI models & inference

Cheapest LLM leaderboard: the 50 lowest-cost AI models available anywhere right now, ranked by inference cost per token across 70+ providers (OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek). Input, output, cache and batch USD per 1M tokens, with context window and capability flags joined in. The one call that answers 'what is the cheapest model I can use?' Refreshed hourly.

Cheapest reasoning-model leaderboard: the 50 lowest-cost AI models with extended reasoning / chain-of-thought support, ranked by inference cost per token — o3, Claude 5 thinking, Gemini 3 Pro, DeepSeek R1, Qwen QwQ and more across 70+ providers. Input, output and cache USD per 1M tokens with context windows joined in. Refreshed hourly.

Cheapest vision/multimodal LLM leaderboard: the 50 lowest-cost AI models that accept image input, ranked by token price across every provider — GPT-5, Claude 5, Gemini 3, Llama 4, Qwen VL and more. Input, output and cache USD per 1M tokens with context window joined in. Answers 'what is the cheapest model that can read images?' in one call. Refreshed hourly.

Largest-context-window leaderboard: the 100 AI models with the biggest context windows, ranked descending — how many tokens each model can actually take, its max output tokens, modality support, and what those tokens cost. Compare GPT-5, Claude 5, Gemini 3 Pro, Llama 4 Scout and 2,000+ more on context capacity and price together. Refreshed hourly.

Microsoft Azure pricing table: per-token cost of every AI model Microsoft Azure serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Microsoft Azure and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

AWS Bedrock pricing table: per-token cost of every AI model AWS Bedrock serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside AWS Bedrock and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Databricks pricing table: per-token cost of every AI model Databricks serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Databricks and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

DeepInfra pricing table: per-token cost of every AI model DeepInfra serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside DeepInfra and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Fireworks AI pricing table: per-token cost of every AI model Fireworks AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Fireworks AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Google AI Studio pricing table: per-token cost of every AI model Google AI Studio serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Google AI Studio and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Mistral AI pricing table: per-token cost of every AI model Mistral AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Mistral AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Nebius pricing table: per-token cost of every AI model Nebius serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Nebius and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Novita AI pricing table: per-token cost of every AI model Novita AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Novita AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

OpenRouter pricing table: per-token cost of every AI model OpenRouter serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside OpenRouter and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

OpenAI pricing table: per-token cost of every AI model OpenAI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside OpenAI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Oracle OCI pricing table: per-token cost of every AI model Oracle OCI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Oracle OCI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Replicate pricing table: per-token cost of every AI model Replicate serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Replicate and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Snowflake Cortex pricing table: per-token cost of every AI model Snowflake Cortex serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Snowflake Cortex and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Vercel AI Gateway pricing table: per-token cost of every AI model Vercel AI Gateway serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Vercel AI Gateway and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Google Vertex AI pricing table: per-token cost of every AI model Google Vertex AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Google Vertex AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

xAI pricing table: per-token cost of every AI model xAI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside xAI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

MiniMax pricing table: what every MiniMax model costs per token right now — MiniMax M2, MiniMax Text — from MiniMax and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare MiniMax inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Mistral pricing table: what every Mistral model costs per token right now — Mistral Large, Mixtral, Codestral, Magistral — from Mistral AI and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Mistral inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Phi pricing table: what every Phi model costs per token right now — Phi-4, Phi-3.5 — from Microsoft and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Phi inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Qwen pricing table: what every Qwen model costs per token right now — Qwen 3, Qwen 2.5, Qwen Coder — from Alibaba and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Qwen inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Grok pricing table: what every Grok model costs per token right now — Grok 4, Grok 4 mini, Grok 3 — from xAI and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Grok inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

Cheapest tool-use LLM leaderboard: the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers. Input, output and cache USD per 1M tokens with context window and modality flags joined in. The cheapest way to pick a model for an agent loop that needs reliable structured tool calls. Refreshed hourly.

SambaNova pricing table: per-token cost of every AI model SambaNova serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside SambaNova and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Cloudflare Workers AI pricing table: per-token cost of every AI model Cloudflare Workers AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Cloudflare Workers AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Anthropic pricing table: per-token cost of every AI model Anthropic serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Anthropic and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.