Tool
LLM API Cost Calculator
Set your token volumes and every model is priced per request, per day and per month. Numbers come straight from each vendor’s published API price list.
Prices updated 2026-10-17.
Prices updated 2026-10-17. Standard tier, no caching or batch discounts.
| Model | Per request | Per day | Per month | Source |
|---|---|---|---|---|
| GPT-6 LunaOpenAI · gpt-6-lunaShort context ≤272K input tokens; long-context rates apply above that.View plan | $0.00045 | $0.45 | $13.50 | developers.openai.com/api/docs/pricing |
| Claude Haiku 5.5Anthropic · claude-haiku-5-5Check Anthropic docs for the exact model ID. Long-context rates apply to prompts over 100,000 tokens.View plan | $0.00045 | $0.45 | $13.50 | platform.claude.com/docs/en/about-claude/pricing |
| DeepSeek V4.1 FlashDeepSeek · deepseek-flashOff-peak price is half (0.15 / 0.60). Peak hours: 01:00–04:00 and 06:00–10:00 UTC on weekdays. | $0.0012 | $1.20 | $36.00 | api-docs.deepseek.com/quick_start/pricing |
| Gemini 3.5 Flash-LiteGoogle · gemini-3.5-flash-liteView plan | $0.00185 | $1.85 | $55.50 | ai.google.dev/gemini-api/docs/pricing |
| Gemini 3.8 FlashGoogle · gemini-3.8-flashPromotional price through December 31, 2026.From 2027-01-01: $1.5/M in · $7.5/M out (calculation uses the current price)View plan | $0.00337 | $3.38 | $101.25 | ai.google.dev/gemini-api/docs/pricing |
| GPT-5.4 MiniOpenAI · gpt-5.4-miniNo long-context tier.View plan | $0.00375 | $3.75 | $112.50 | developers.openai.com/api/docs/pricing |
| DeepSeek V4 ProDeepSeek · deepseek-v4-proOff-peak price is half (0.66 / 1.98). | $0.00462 | $4.62 | $138.60 | api-docs.deepseek.com/quick_start/pricing |
| GPT-6.1 SolOpenAI · gpt-6.1-solShort context ≤272K input tokens; long-context rates apply above that.View plan | $0.009 | $9.00 | $270.00 | developers.openai.com/api/docs/pricing |
| Claude Sonnet 5.5Anthropic · claude-sonnet-5-5Check Anthropic docs for the exact model ID.View plan | $0.009 | $9.00 | $270.00 | platform.claude.com/docs/en/about-claude/pricing |
| Gemini 3.1 Pro PreviewGoogle · gemini-3.1-pro-previewLong-context rates apply above 200,000 input tokens.View plan | $0.01 | $10.00 | $300.00 | ai.google.dev/gemini-api/docs/pricing |
| Claude Opus 5.5Anthropic · claude-opus-5-5Check Anthropic docs for the exact model ID.View plan | $0.02 | $18.00 | $540.00 | platform.claude.com/docs/en/about-claude/pricing |
| GPT-6 AstraOpenAI · gpt-6-astraShort context ≤272K input tokens; long-context rates apply above that.View plan | $0.04 | $45.00 | $1350.00 | developers.openai.com/api/docs/pricing |
| Claude Fable 5.1Anthropic · claude-fable-5-1Check Anthropic docs for the exact model ID.View plan | $0.04 | $45.00 | $1350.00 | platform.claude.com/docs/en/about-claude/pricing |
How this is calculated
Cost per request = input tokens × the model’s input price plus output tokens × its output price, both quoted per 1M tokens. Cost per day multiplies that by requests per day, and per month by days per month. If your input tokens per request exceed a model’s long-context threshold, the long-context rates apply to the whole request.
Prices are the standard (non-batch) tier and assume no prompt caching or batch discounts. Some models publish a scheduled price change; the estimate uses today’s price and the table notes the upcoming one. Always confirm against the linked vendor pricing page before budgeting.