LLM models

Pricing updated daily · Last refreshed Oct 29, 2026

30 models across 6 providers, with the prices and limits that decide cost. Open a model for example workloads and cheaper alternatives, or use the comparison tool to filter and export.

Rankings

Rule-based lists over listed prices and specs. They rank by price and size, not by output quality, which this site does not measure.

OpenAI

OpenAI models
ModelProviderContextInput $/1MOutput $/1M
GPT-6 Luna ProOpenAI1.05M$0.10$0.50
GPT-6.1 SolOpenAI1.05M$2.00$10.00
GPT-6.1 Sol ProOpenAI1.05M$2.00$10.00
GPT-6.1 TerraOpenAI1.05M$1.00$5.00
GPT-6.1 Terra ProOpenAI1.05M$1.00$5.00

Anthropic

Anthropic models
ModelProviderContextInput $/1MOutput $/1M
Claude Fable 5.1Anthropic1M$10.00$50.00
Claude Haiku 5.5Anthropic1M$0.10$0.50
Claude Opus 5Anthropic1M$5.00$25.00
Claude Opus 5.5Anthropic1M$4.00$20.00
Claude Sonnet 5.5Anthropic1M$2.00$10.00

Google

Google models
ModelProviderContextInput $/1MOutput $/1M
Gemini 3.6 FlashGoogle1.05M$0.75$3.75
Gemini 3.7 FlashGoogle1.05M$0.75$3.75
Gemini 3.8 FlashGoogle1.05M$0.825$4.125
Gemini 4 ArgonGoogle1.05M$2.00$10.00
Nano Banana 2.1Google66K$1.50$7.50

Meta

Meta models
ModelProviderContextInput $/1MOutput $/1M
Llama 3.2 1B InstructMeta60K$0.027$0.201
Llama 3.3 70B InstructMeta131K$0.10$0.32
Llama 4 MaverickMeta524K$0.188$0.652
Llama 4 ScoutMeta1.31M$0.10$0.30
Llama Guard 4 12BMeta164K$0.18$0.18

Mistral

Mistral models
ModelProviderContextInput $/1MOutput $/1M
Devstral 2 2512Mistral262K$0.40$2.00
Ministral 3 14B 2512Mistral262K$0.20$0.20
Mistral Large 4Mistral1.05M$0.70$2.10
Mistral Medium 3.5Mistral262K$1.50$7.50
Mistral Small 4Mistral262K$0.15$0.60

Cohere

Cohere models
ModelProviderContextInput $/1MOutput $/1M
Command ACohere256K$2.50$10.00
Command A+Cohere192K$0.30$1.50
Command R (08-2024)Cohere128K$0.15$0.60
Command R+ (08-2024)Cohere128K$2.50$10.00
Command R7B (12-2024)Cohere128K$0.037$0.15

Want to sort, filter or export? Use the model comparison tool. Prices are those OpenRouter charges and can differ from a provider’s own list price.

llmtools is a vendor-neutral toolkit for working with large language models — token counting, cost estimation and model comparison, computed in your browser. OpenAI token counts are exact, using the same encoding the model does (o200k_base for GPT-4o, cl100k_base for GPT-4/3.5); Claude and Gemini counts are labelled approximations, since neither publishes a tokenizer that runs client-side. Model pricing is read from OpenRouter’s public catalogue once a day. Nothing you type is ever transmitted anywhere.