LLM cost planner
LLM Cost Calculator
Estimate monthly and annual API spend using requests/day, input tokens, output tokens, retry rate, and cache hit rate. Built for coding agents, RAG apps, support bots, and batch extraction jobs.
Model cost comparison
Default estimates below use the Coding agent preset. Change the scenario above for your own traffic and token mix.
| Model | Provider | Input | Output | Monthly estimate | Annual estimate | Source |
|---|---|---|---|---|---|---|
| 1. GPT-OSS-120B Free — open weights, self-hosted | OpenAI | $0/M | $0/M | $0.00 | $0.00 | Source 2026-09-20 |
| 2. Qwen3.8-Flash QwenCloud list prices per MTok; implicit cache reads are $0.016/MTok. | Alibaba / Qwen | $0.15/M | $0.47/M | $18.70 | $224 | Source 2026-09-20 |
| 3. GLM-5.3-Flash Standard Z.ai API list pricing per MTok; cached input is $0.03/MTok. | Z.ai | $0.15/M | $0.5/M | $19.14 | $230 | Source 2026-09-20 |
| 4. DeepSeek V4.1 Flash Off-peak list price per MTok. Peak rates are $0.30 input / $1.20 output; cache-hit input is $0.003 off-peak or $0.006 peak. Peak hours are 01:00–04:00 and 06:00–10:00 UTC on weekdays. | DeepSeek | $0.15/M | $0.6/M | $20.59 | $247 | Source 2026-09-20 |
| 5. GPT-5.6 Luna Standard API price per MTok below 272K input tokens. Above that threshold, pricing is $0.40 input / $1.80 output per MTok. | OpenAI | $0.2/M | $1.2/M | $33.29 | $399 | Source 2026-09-20 |
| 6. Gemini 3.5 Flash-Lite Standard paid tier; Batch and Flex tiers are lower. | $0.3/M | $2.5/M | $60.14 | $722 | Source 2026-09-20 | |
| 7. DeepSeek V4 Pro Off-peak list price per MTok. DeepSeek continued the dedicated V4 Pro API after September 14; peak rates are $1.32 input / $3.96 output and cache-hit input is $0.022 off-peak or $0.044 peak. Peak hours are 01:00–04:00 and 06:00–10:00 UTC on weekdays. | DeepSeek | $0.66/M | $1.98/M | $80.99 | $972 | Source 2026-09-20 |
| 8. Gemini 3.8 Flash Introductory paid-tier pricing per MTok through December 31, 2026; standard pricing becomes $1.50 input / $7.50 output on January 1, 2027. | $0.75/M | $3.75/M | $114 | $1,367 | Source 2026-09-20 | |
| 9. Gemini 3.7 Flash Introductory paid-tier pricing per MTok through December 31, 2026; standard pricing becomes $1.50 input / $7.50 output on January 1, 2027. | $0.75/M | $3.75/M | $114 | $1,367 | Source 2026-09-20 | |
| 10. Gemini 3.8 Live Published text rates per MTok. Audio input is $3/MTok (about $0.005/min) and audio output is $12/MTok (about $0.018/min); image/video input is $1/MTok (about $0.002/min). | $0.75/M | $4.5/M | $125 | $1,498 | Source 2026-09-20 | |
| 11. Gemini 3.8 Live Extended Thinking Published text rates per MTok. Audio input is $3/MTok (about $0.005/min) and audio output is $12/MTok (about $0.018/min); image/video input is $1/MTok (about $0.002/min). | $0.75/M | $4.5/M | $125 | $1,498 | Source 2026-09-20 | |
| 12. GLM-5 | Zhipu AI | $1/M | $3.2/M | $126 | $1,508 | Source 2026-09-20 |
| 13. Kimi K2.7 Code Standard Kimi API cache-miss price per MTok; cache-hit input is $0.19/MTok. The higher-throughput variant is $0.38 cached input / $1.90 cache-miss input / $8 output per MTok. | Moonshot AI | $0.95/M | $4/M | $133 | $1,600 | Source 2026-09-20 |
| 14. Claude Haiku 4.5 | Anthropic | $1/M | $5/M | $152 | $1,823 | Source 2026-09-20 |
| 15. GLM-5.3 Standard Z.ai API pricing per MTok; cached-input pricing is $0.26/MTok. | Z.ai | $1.4/M | $4.4/M | $175 | $2,097 | Source 2026-09-20 |
| 16. Gemini 3.6 Flash Standard paid tier; Batch and Flex tiers are lower. | $1.5/M | $7.5/M | $228 | $2,734 | Source 2026-09-20 | |
| 17. Mistral Medium 3.5 | Mistral | $1.5/M | $7.5/M | $228 | $2,734 | Source 2026-09-20 |
| 18. Grok 4.5 Standard context pricing. Prompts at or above 200K tokens use xAI’s higher long-context rates. | xAI | $2/M | $6/M | $245 | $2,945 | Source 2026-09-20 |
| 19. Grok 4.6 Per MTok below 200K prompt tokens; cached input is $0.50/MTok. Prompts at or above 200K use $4 input / $1 cached input / $12 output per MTok. | xAI | $2/M | $6/M | $245 | $2,945 | Source 2026-09-20 |
| 20. Gemini 3.5 Flash Standard tier; Batch and Flex tiers are lower. | $1.5/M | $9/M | $250 | $2,996 | Source 2026-09-20 | |
| 21. Claude Sonnet 5 Standard list price per MTok. Anthropic cancelled the previously scheduled September 1, 2026 increase. | Anthropic | $2/M | $10/M | $304 | $3,645 | Source 2026-09-20 |
| 22. GPT-5.6 Terra Standard API price per MTok below 272K input tokens. Above that threshold, pricing is $4 input / $18 output per MTok. | OpenAI | $2/M | $12/M | $333 | $3,995 | Source 2026-09-20 |
| 23. GPT-5.2-Codex | OpenAI | $1.75/M | $14/M | $342 | $4,108 | Source 2026-09-20 |
| 24. GPT-5.2 | OpenAI | $1.75/M | $14/M | $342 | $4,108 | Source 2026-09-20 |
| 25. GPT-5.4 | OpenAI | $2.5/M | $15/M | $416 | $4,994 | Source 2026-09-20 |
| 26. Kimi K3 Kimi lists $0.30/MTok cached input, $3/MTok input, and $15/MTok output. | Moonshot AI | $3/M | $15/M | $456 | $5,468 | Source 2026-09-20 |
| 27. GPT-5.6 Sol Promotional API pricing per MTok, available at least through November 21, 2026, per OpenAI. | OpenAI | $4/M | $20/M | $608 | $7,290 | Source 2026-09-20 |
| 28. Claude Opus 5 | Anthropic | $5/M | $25/M | $759 | $9,113 | Source 2026-09-20 |
| 29. Claude Opus 4.8 | Anthropic | $5/M | $25/M | $759 | $9,113 | Source 2026-09-20 |
| 30. GPT-5.5 | OpenAI | $5/M | $30/M | $832 | $9,987 | Source 2026-09-20 |