Overage / Compare / LLM APIs
Anthropic API vs Google Gemini API pricing Monthly cost at three volumes Monthly cost of Anthropic API and Google Gemini API at three volumes and at your own Volume Anthropic APICheapest model Claude Fable 5.1 Claude Opus 5.5 Claude Sonnet 5.5 Claude Haiku 5.5 (prompt <=100K tokens) Claude Haiku 5.5 (prompt >100K tokens) Claude Mythos 5.1 Claude Fable 5 Claude Mythos 5 Claude Opus 5 Claude Opus 4.8 Claude Opus 4.7 Claude Opus 4.6 Claude Opus 4.5 Claude Opus 4.1 Claude Opus 4 Claude Sonnet 5 Claude Sonnet 4.6 Claude Sonnet 4.5 Claude Sonnet 4 Claude Haiku 4.5 Claude Haiku 3.5 Google Gemini APICheapest model Gemini 4 Argon (Standard) Gemini 4 Argon (Batch) Gemini 4 Argon (Flex) Gemini 4 Argon (Priority) Gemini 3.8 Flash (Standard) Gemini 3.8 Flash (Batch) Gemini 3.8 Flash (Flex) Gemini 3.8 Flash (Priority) Gemini 3.6 Flash (Standard) Gemini 3.6 Flash (Batch) Gemini 3.6 Flash (Flex) Gemini 3.6 Flash (Priority) Gemini 3.5 Flash-Lite Gemini 3.1 Flash-Lite Gemini Omni Flash Gemini 3.1 Pro Preview (prompt <=200K tokens) Gemini 3.1 Pro Preview (prompt >200K tokens) Gemini Nano Banana 2.1 Gemini 3.1 Flash Image (Nano Banana 2) Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) Gemini 3.8 Flash TTS Gemini 3.8 Flash-Lite TTS Gemini 3.1 Flash TTS Preview Gemini 3 Flash Preview Gemini 3 Pro Image (Nano Banana Pro) Gemini 2.5 Pro (prompt <=200k tokens) Gemini 2.5 Pro (prompt >200k tokens) Gemini 2.5 Flash-Lite Gemini 2.5 Flash Native Audio (Live API) Gemini 2.5 Flash Preview TTS Gemini 2.5 Pro Preview TTS Gemini Embedding 2 Gemini 3.8 Live Gemini 3.8 Live Extended Thinking Gemini 3.1 Flash Live Preview Gemini Robotics ER 2 Preview Gemini Robotics ER 2 Streaming Preview small1M input, 200K output $0.20 / moClaude Haiku 5.5 (prompt <=100K tokens) $0.18 / moGemini 2.5 Flash-Lite growing50M input, 10M output $10 / moClaude Haiku 5.5 (prompt <=100K tokens) $9 / moGemini 2.5 Flash-Lite scale1B input, 200M output $200 / moClaude Haiku 5.5 (prompt <=100K tokens) $180 / moGemini 2.5 Flash-Lite your volumeset above $10 / moClaude Haiku 5.5 (prompt <=100K tokens) $9 / moGemini 2.5 Flash-Lite
Each cell is the cheapest feasible plan, or the chosen model, at that volume, from the shared Overage cost function. "Cheapest model" only considers models with both an input and an output price listed. Volumes are example scenarios you can edit.
Cheapest model per service, USD per 1M tokens Cheapest priced model of each service Service Cheapest model Input Output Models listed Anthropic API Claude Haiku 5.5 (prompt <=100K tokens) $0.10 $0.50 21 Google Gemini API Gemini 2.5 Flash-Lite $0.10 $0.40 37
Every model Every model of both services, USD per 1M tokens Model Service Input Output Claude Haiku 5.5 (prompt <=100K tokens) Anthropic API $0.10 $0.50 Claude Haiku 5.5 (prompt >100K tokens) Anthropic API $0.50 $2.50 Claude Haiku 3.5 Anthropic API $0.80 $4 Claude Haiku 4.5 Anthropic API $1 $5 Claude Sonnet 5.5 Anthropic API $2 $10 Claude Sonnet 5 Anthropic API $2 $10 Claude Sonnet 4.6 Anthropic API $3 $15 Claude Sonnet 4.5 Anthropic API $3 $15 Claude Sonnet 4 Anthropic API $3 $15 Claude Opus 5.5 Anthropic API $4 $20 Claude Opus 5 Anthropic API $5 $25 Claude Opus 4.8 Anthropic API $5 $25 Claude Opus 4.7 Anthropic API $5 $25 Claude Opus 4.6 Anthropic API $5 $25 Claude Opus 4.5 Anthropic API $5 $25 Claude Fable 5.1 Anthropic API $10 $50 Claude Mythos 5.1 Anthropic API $10 $50 Claude Fable 5 Anthropic API $10 $50 Claude Mythos 5 Anthropic API $10 $50 Claude Opus 4.1 Anthropic API $15 $75 Claude Opus 4 Anthropic API $15 $75 Gemini 2.5 Flash-Lite Google Gemini API $0.10 $0.40 Gemini Embedding 2 Google Gemini API $0.20 unlisted Gemini 3.1 Flash-Lite Google Gemini API $0.25 $1.50 Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) Google Gemini API $0.25 $1.50 Gemini 3.5 Flash-Lite Google Gemini API $0.30 $2.50 Gemini 3.8 Flash (Flex) Google Gemini API $0.375 $1.875 Gemini 3.6 Flash (Flex) Google Gemini API $0.375 $1.875 Gemini 3.1 Flash Image (Nano Banana 2) Google Gemini API $0.50 $3 Gemini 3.8 Flash TTS Google Gemini API $0.50 unlisted Gemini 3.8 Flash-Lite TTS Google Gemini API $0.50 unlisted Gemini 3 Flash Preview Google Gemini API $0.50 $3 Gemini 2.5 Flash Native Audio (Live API) Google Gemini API $0.50 $2 Gemini 2.5 Flash Preview TTS Google Gemini API $0.50 unlisted Gemini 3.8 Flash (Standard) Google Gemini API $0.75 $3.75 Gemini 3.6 Flash (Standard) Google Gemini API $0.75 $3.75 Gemini 3.8 Live Google Gemini API $0.75 $4.50 Gemini 3.8 Live Extended Thinking Google Gemini API $0.75 $4.50 Gemini 3.1 Flash Live Preview Google Gemini API $0.75 $4.50 Gemini 4 Argon (Flex) Google Gemini API $1 $5 Gemini 3.1 Flash TTS Preview Google Gemini API $1 unlisted Gemini 2.5 Pro Preview TTS Google Gemini API $1 unlisted Gemini Robotics ER 2 Preview Google Gemini API $1 $5 Gemini Robotics ER 2 Streaming Preview Google Gemini API $1 $5 Gemini 2.5 Pro (prompt <=200k tokens) Google Gemini API $1.25 $10 Gemini 3.8 Flash (Priority) Google Gemini API $1.35 $6.75 Gemini 3.6 Flash (Priority) Google Gemini API $1.35 $6.75 Gemini Omni Flash Google Gemini API $1.50 $9 Gemini Nano Banana 2.1 Google Gemini API $1.50 $7.50 Gemini 4 Argon (Standard) Google Gemini API $2 $10 Gemini 3.1 Pro Preview (prompt <=200K tokens) Google Gemini API $2 $12 Gemini 2.5 Pro (prompt >200k tokens) Google Gemini API $2.50 $15 Gemini 4 Argon (Priority) Google Gemini API $3.60 $18 Gemini 3.1 Pro Preview (prompt >200K tokens) Google Gemini API $4 $18 Gemini 4 Argon (Batch) Google Gemini API unlisted unlisted Gemini 3.8 Flash (Batch) Google Gemini API unlisted unlisted Gemini 3.6 Flash (Batch) Google Gemini API unlisted unlisted Gemini 3 Pro Image (Nano Banana Pro) Google Gemini API unlisted $12
Models are compared by name and price, never by position. Pick one model per service, or "Cheapest model", in the cost table above.
Tiers, aligned by position Tiers of Anthropic API and Google Gemini API aligned by position: free, entry, mid, top Position Anthropic API Google Gemini API Free no tier $0 / mo Free Entry no tier Contact sales Enterprise Mid no tier no tier Top no tier no tier
Tightest rate limit Tightest documented rate limit of each service Measure Anthropic API Google Gemini API Tightest limit unlisted unlisted
Changes in the last 90 days Before not listed → After $2 input, $10 output per 1M tokens new