54 Services from modelprices.xyz
Returns live per-token pricing data for 2,000+ LLMs across 70+ providers, normalized into a single table with input, output, cache, and batch rates in USD per 1M tokens.
$0.02/messageReturns the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers, with input/output/cache pricing and context window details.
$0.01/messageReturns the lowest-cost AI models matching capability constraints (context window, vision, function calling, reasoning) across 2,000+ models and 70+ providers
$0.01/messageReturns per-token pricing for every AI model available on Google Vertex AI, including input, output, cache, and batch costs in USD per 1M tokens, ranked cheapest first with context window and capability metadata.
$0.01/messageReturns a comprehensive table of capability specs and constraints for 2,000+ LLMs, including context window size, max output tokens, and feature support flags (vision, audio, function-calling, reasoning).
$0.02/messageReturns the full per-token pricing table for every AI model available through Vercel AI Gateway, ranked cheapest first, with input/output/cache/batch USD costs per 1M tokens, context window sizes, and capability flags.
$0.01/messageReturns the 50 lowest-cost AI models across 70+ providers, ranked by inference cost per token, including input, output, cache, and batch pricing in USD per 1M tokens.
$0.01/messageReturns the 50 lowest-cost AI models with a 200,000+ token context window, ranked by inference cost per token, with input/output/cache pricing in USD per 1M tokens.
$0.01/messageReturns a ranked table of per-token USD costs (input, output, cache, batch) for every AI model available on Microsoft Azure, sorted cheapest first, with context window sizes and capability flags.
$0.01/messageReturns current per-token USD pricing (input, output, cache, batch) for a specific AI model by ID, with fuzzy matching on model names.
$0.003/messageReturns current per-token pricing for all GPT models (GPT-5, GPT-4o, GPT-4.1, o3, etc.) across every host that serves them — OpenAI, Azure, Bedrock, Vertex, OpenRouter, Fireworks — sorted cheapest first.
$0.01/messageReturns per-token USD costs for every AI model available on OpenRouter, sorted cheapest first, with context window sizes and capability flags.
$0.01/messageReturns per-token pricing for every AI model available on Cloudflare Workers AI, including input, output, cache, and batch costs in USD per 1M tokens, ranked cheapest first with context window and capability flags.
$0.01/messageReturns per-token USD costs for every OpenAI model in a single call, including input, output, cache, and batch pricing ranked cheapest first with context window and capability metadata.
$0.01/messageReturns a complete, ranked pricing table for every AI model served by Fireworks AI, including input, output, cache, and batch costs in USD per 1M tokens, plus context window and capability flags.
$0.01/messageReturns per-token USD costs for every AI model available on AWS Bedrock, including input, output, cache, and batch pricing, ranked cheapest first with context window and capability metadata.
$0.01/messageReturns a structured JSON feed of recent AI model pricing changes — old vs new token cost, percent delta, timestamps, plus newly launched and removed models — diffed from hourly snapshots across all major providers.
$0.03/messageReturns per-token USD pricing for every AI model available on Replicate, ranked cheapest first, with context window and capability flags.
$0.01/messageReturns real-time per-token pricing for all Claude models (Claude 5, Opus, Sonnet, Haiku) across every provider that hosts them, sorted cheapest first
$0.01/messageReturns per-token pricing for every AI model available on Snowflake Cortex, including input, output, cache, and batch costs in USD per 1M tokens, ranked cheapest first with context window and capability flags.
$0.01/messageReturns per-token USD costs for every Anthropic-served AI model in a single call, including input, output, cache, and batch pricing, context window sizes, and capability flags, ranked cheapest first.
$0.01/messageReturns a ranked table of per-token USD costs for every AI model served by Databricks, including input, output, cache, and batch pricing plus context window and capability flags.
$0.01/messageReturns a normalized, cross-provider pricing table for all Llama models (input, output, cache, batch USD per 1M tokens), sorted cheapest first, refreshed hourly.
$0.01/messageReturns the 50 lowest-cost AI models with extended reasoning/chain-of-thought support, ranked by inference cost per token, including input/output/cache pricing and context window sizes across 70+ providers.
$0.01/messageReturns a ranked, normalized pricing table for every AI model available on IBM watsonx, including per-token costs for input, output, cache, and batch usage in USD per 1M tokens, with context window size and capability flags.
$0.01/messageReturns a ranked table of per-token USD costs (input, output, cache, batch) for every AI model available on Oracle OCI, including context window sizes and capability flags, refreshed hourly.
$0.01/messageReturns the 50 lowest-cost AI models with at least a 128,000-token context window, ranked by inference cost per token across 70+ providers, with input/output/cache pricing in USD per 1M tokens.
$0.01/messageReturns per-token pricing for all Jamba models (Jamba 1.5 Large, Jamba Mini) across every provider that hosts them, sorted cheapest first.
$0.01/messageReturns per-token USD pricing for every AI model served by Mistral AI, including input, output, cache, and batch costs, ranked cheapest first, with context window sizes and capability flags.
$0.01/messageReturns per-token pricing for all GLM models (GLM-4.6, GLM-4.5 Air) across every provider that hosts them, sorted cheapest first.
$0.01/messageReturns current per-token pricing for all MiniMax models (M2, Text) across every provider that hosts them, including AWS Bedrock, Azure, Vertex, OpenRouter, and Fireworks, sorted cheapest first.
$0.01/messageReturns current per-token pricing for all Phi models (Phi-4, Phi-3.5) across every provider that hosts them, sorted cheapest first.
$0.01/messageReturns per-token pricing for all Kimi models (Kimi K2, Moonshot v1) across every provider that hosts them, sorted cheapest first
$0.01/messageReturns per-token USD pricing for every AI model available on DeepInfra, including input, output, cache, and batch costs per 1M tokens, sorted cheapest first, with context window and capability flags.
$0.01/messageReturns per-token pricing for every AI model available on SambaNova, including input, output, cache, and batch costs in USD per 1M tokens, with context window sizes and capability flags, ranked cheapest first.
$0.01/messageReturns per-token USD costs for every AI model hosted on Together AI, ranked cheapest first, with context window sizes and capability flags included.
$0.01/messageReturns current per-token pricing for all Command models (Command A, Command R+, Command R) across every host including Cohere, Bedrock, Azure, Vertex, OpenRouter, and Fireworks, sorted cheapest first.
$0.01/messageReturns current per-token pricing for all Gemini models across every host (Google, Bedrock, Azure, Vertex, OpenRouter, Fireworks), sorted cheapest first.
$0.01/messageReturns current per-token pricing for all DeepSeek models (V4, R1, Coder, etc.) across every provider that hosts or resells them, sorted cheapest first.
$0.01/messageReturns current per-token pricing for all Gemma models (Gemma 3, Gemma 2) across every host provider, sorted cheapest first.
$0.01/messageReturns a normalized pricing dataset for 2,000+ LLM models across 70+ providers, including token costs for input/output, refreshed hourly
$0.02/messageReturns current per-token pricing for all Grok models (Grok 4, Grok 4 mini, Grok 3) across every provider that hosts them, sorted cheapest first.
$0.01/messageReturns per-token pricing for every Qwen model across all major hosting providers, sorted cheapest first, refreshed hourly.
$0.01/messageReturns context window size, max output tokens, and feature support flags (vision, audio, function calling, reasoning) for a single AI model by ID.
$0.003/messageReturns a ranked list of every AI model with a 1M+ token context window, sorted by inference cost per token, with input/output/cache pricing in USD per 1M tokens.
$0.01/messageReturns the top 100 AI models ranked by context window size (descending), with token limits, max output tokens, modality support, and per-token pricing.
$0.01/messageReturns per-token USD pricing for every AI model served by xAI, ranked cheapest first, with context window sizes and capability flags included.
$0.01/messageReturns the 50 lowest-cost AI models that accept image input, ranked by token price across all providers, with input, output, and cache pricing per 1M tokens.
$0.01/messageReturns a ranked pricing table of every AI model available on Google AI Studio, including input, output, cache, and batch costs in USD per 1M tokens, with context window sizes and capability flags.
$0.01/messageReturns per-token USD pricing for every AI model hosted on Nebius, ranked cheapest first, with context window sizes and capability flags.
$0.01/messageReturns per-token pricing for every AI model served by Novita AI, including input, output, cache, and batch costs in USD per 1M tokens, sorted cheapest first, with context window sizes and capability flags.
$0.01/messageReturns current per-token pricing for all Mistral AI models across every major host (Mistral, Bedrock, Azure, Vertex, OpenRouter, Fireworks), sorted cheapest first.
$0.01/messageReturns current per-token pricing (input, output, cache) for a single LLM by model ID, normalized across 70+ providers.
$0.003/messageReturns context window size, max output tokens, and capability flags (vision, audio, etc.) for a single LLM model by ID
$0.003/message