TokenCost Lab
Home
Sandbox
Compare
💰
ROI Calculator
📊
Side-by-Side Compare
Balanced (60:40)
RAG & Search (85:15)
Agent & Gen (25:75)
Ideal for general chatbots, customer service, and standard multi-turn interactive sessions.
Current Model
Amazon Nova Lite (amazon)
Amazon Nova Micro (amazon)
Amazon Nova Premier (amazon)
Amazon Nova Pro (amazon)
Claude 3 Haiku (anthropic)
Claude 3 Opus (anthropic)
Claude 3.5 Haiku (anthropic)
Claude 3.5 Sonnet (anthropic)
Claude 3.7 Sonnet (anthropic)
Claude 4.5 Haiku (anthropic)
Claude Opus 4 (anthropic)
Claude Opus 4.1 (anthropic)
Claude Opus 4.5 (anthropic)
Claude Sonnet 4 and 4.5 >200k (anthropic)
Claude Sonnet 4 and 4.5 ≤200k (anthropic)
DeepSeek Chat (deepseek)
DeepSeek Reasoner (deepseek)
DeepSeek-V4-Flash (deepseek)
DeepSeek-V4-Pro (deepseek)
Gemini 1.5 Flash >128k (google)
Gemini 1.5 Flash ≤128k (google)
Gemini 1.5 Flash-8B >128k (google)
Gemini 1.5 Flash-8B ≤128k (google)
Gemini 1.5 Pro >128k (google)
Gemini 1.5 Pro ≤128k (google)
Gemini 2.0 Flash (google)
Gemini 2.0 Flash Lite (google)
Gemini 2.5 Flash (google)
Gemini 2.5 Flash Preview (09-2025) (google)
Gemini 2.5 Flash-Lite (google)
Gemini 2.5 Pro >200k (google)
Gemini 2.5 Pro ≤200k (google)
Gemini 2.5 Pro Preview >200k (google)
Gemini 2.5 Pro Preview ≤200k (google)
Gemini 3 Flash Preview (google)
Gemini 3 Pro >200k (google)
Gemini 3 Pro ≤200k (google)
Gemini 3.1 Flash-Lite (google)
Gemini 3.1 Pro >200k (google)
Gemini 3.1 Pro ≤200k (google)
Gemini 3.5 Flash (google)
MiniMax M2 (minimax)
Codestral (mistral)
Magistral Medium (mistral)
Ministral 3B 24.10 (mistral)
Ministral 8B 24.10 (mistral)
Mistral 7B (mistral)
Mistral Large 24.11 (mistral)
Mistral Medium 3 (mistral)
Mistral NeMo (mistral)
Mistral Saba (mistral)
Mistral Small 3.1 (mistral)
Mixtral 8x22B (mistral)
Mixtral 8x7B (mistral)
Pixtral 12B (mistral)
Pixtral Large (mistral)
Kimi K2 0711 Preview (moonshot-ai)
Kimi K2 0905 Preview (moonshot-ai)
Kimi K2 Thinking (moonshot-ai)
Kimi K2 Thinking Turbo (moonshot-ai)
Kimi K2 Turbo Preview (moonshot-ai)
ChatGPT 4o Latest (openai)
GPT-3 Text Davinci 003 (openai)
GPT-4.1 (openai)
GPT-4.1 Mini (openai)
GPT-4.1 Nano (openai)
GPT-4.5 (openai)
GPT-4o (openai)
GPT-4o Mini (openai)
GPT-5 (openai)
GPT-5 Mini (openai)
GPT-5 Nano (openai)
GPT-5 Pro (openai)
GPT-5.1 (openai)
GPT-5.1 Codex (openai)
GPT-5.1 Codex mini (openai)
GPT-5.2 (openai)
GPT-5.2 Pro (openai)
GPT-5.4 >272k (openai)
GPT-5.4 ≤272k (openai)
GPT-5.4 Mini (openai)
GPT-5.4 Nano (openai)
GPT-5.4 Pro >272k (openai)
GPT-5.4 Pro ≤272k (openai)
GPT-5.5 >272k (openai)
GPT-5.5 ≤272k (openai)
GPT-5.5 Pro ≤272k (openai)
gpt-image-1 (image gen) (openai)
gpt-image-1-mini (image gen) (openai)
gpt-image-2 (image gen) image tokens (openai)
gpt-image-2 (image gen) text tokens (openai)
o1 and o1-preview (openai)
o1 Pro (openai)
o1-mini (openai)
o3 (openai)
o3 Deep Research (openai)
o3 Pro (openai)
o3-mini (openai)
o4-mini (openai)
o4-mini Deep Research (openai)
Qwen3.6 Plus >256k (qwen)
Qwen3.6 Plus ≤256k (qwen)
Grok 3 (xai)
Grok 3 Mini (xai)
Grok 4 >128k (xai)
Grok 4 ≤128k (xai)
Grok 4 Fast (xai)
Grok 4 Fast >128k (xai)
Grok 4 Fast ≤128k (xai)
Grok 4 Fast Reasoning >128k (xai)
Grok 4 Fast Reasoning ≤128k (xai)
Grok Code Fast 1 (xai)
Current Monthly Spend ($)
No cost-saving alternatives found or current model is already optimal for cost.