Living registry · synced July 31, 2026

Find the right model for the job.

Compare context, input, cached-input, and output rates in one place. Every row links to the pricing page it came from, so you can re-check before production billing.

How to read this tableRates are USD per 1M tokens. “—” means the provider does not publish a separate cached-input rate. Regional, batch, long-context, and search-request surcharges can change the final bill.
ModelProviderContextInput / 1MCached / 1MOutput / 1MFit & source
Claude Fable 5Fable 5 · claude-fable-5Anthropic1,000,000$10$1$50FlagshipOfficial · 2026-07-31Provider source ↗
Claude Opus 5Opus 5 · claude-opus-5Anthropic1,000,000$5$0.5$25FlagshipOfficial · 2026-07-31Provider source ↗
Claude Sonnet 5Sonnet 5 · claude-sonnet-5Introductory pricing through Aug 31, 2026; standard price becomes $3/$15.Anthropic1,000,000$2$0.2$10BalancedOfficial · 2026-07-31Provider source ↗
Claude Haiku 4.5Haiku 4.5 · claude-haiku-4-5Anthropic200,000$1$0.1$5FastOfficial · 2026-07-31Provider source ↗
GPT-5.6 SolGPT-5.6 · gpt-5.6-solShort-context price; prompts over 272K use a higher long-context tier.OpenAI1,050,000$5$0.5$30FlagshipOfficial · 2026-07-31Provider source ↗
GPT-5.6 TerraGPT-5.6 · gpt-5.6-terraShort-context price; prompts over 272K use a higher long-context tier.OpenAI1,050,000$2$0.2$12BalancedOfficial · 2026-07-31Provider source ↗
GPT-5.6 LunaGPT-5.6 · gpt-5.6-lunaShort-context price; prompts over 272K use a higher long-context tier.OpenAI1,050,000$0.2$0.02$1.2FastOfficial · 2026-07-31Provider source ↗
Gemini 3.1 Pro PreviewGemini 3.1 · gemini-3.1-pro-previewStandard price for prompts up to 200K; larger prompts are tiered at $4/$18.Google1,000,000$2$0.2$12FlagshipOfficial · 2026-07-31Provider source ↗
Gemini 3.6 FlashGemini 3.6 · gemini-3.6-flashGoogle1,000,000$1.5$0.15$7.5FastOfficial · 2026-07-31Provider source ↗
Gemini 3.5 Flash-LiteGemini 3.5 · gemini-3.5-flash-liteGoogle1,000,000$0.3$0.03$2.5FastOfficial · 2026-07-31Provider source ↗
Grok 4.5Grok 4.5 · grok-4.5xAI publishes input/output pricing; no cached-input rate listed.xAI500,000$2$6BalancedOfficial · 2026-07-31Provider source ↗
Kimi K3Kimi K3 · kimi-k3Moonshot1,048,576$3$0.3$15BalancedOfficial · 2026-07-31Provider source ↗
DeepSeek V4 ProDeepSeek V4 · deepseek-v4-proDeepSeek1,000,000$0.435$0.003625$0.87BalancedOfficial · 2026-07-31Provider source ↗
DeepSeek V4 FlashDeepSeek V4 · deepseek-v4-flashDeepSeek1,000,000$0.14$0.0028$0.28FastOfficial · 2026-07-31Provider source ↗
Qwen 3 235BQwen 3 · qwen3-235b-a22bInternational standard price; Qwen pricing varies by deployment region and mode.Alibaba262,000$0.7$2.8OpenOfficial · 2026-07-31Provider source ↗
Llama 4 MaverickLlama 4 · meta-llama/llama-4-maverickHosted-provider reference; self-hosted Llama has no universal per-token price.Meta1,000,000$0.2$0.8OpenProvider-specific · 2026-07-31Provider source ↗
Mistral Large 3Mistral Large · mistral-large-latestMistral256,000$0.5$1.5OpenOfficial · 2026-07-31Provider source ↗
Command ACommand A · command-a-03-2025Cohere256,000$2.5$10BalancedOfficial · 2026-07-31Provider source ↗
Sonar ProSonar · sonar-proToken price excludes Sonar search-context request fees ($6/$10/$14 per 1K requests).Perplexity200,000$3$15BalancedOfficial · 2026-07-31Provider source ↗