Suggestion tool
AI Model Cost Calculator
Set how many tokens a typical task reads and writes, how much of the input is cached, and how many tasks you run. We price it on every model with listed per-token prices.
50,000 in and 5,000 out per task, 0% cached, 20 tasks a day for 22 days: 440 tasks a month across 84 models.
| Model | Maker | In / out per 1M | Per task | Per month |
|---|---|---|---|---|
| Gemma 4 26B A4B | $0.03 / $0.08, cached $0.04 | <$0.01 | $0.72 | |
| gpt-oss-20b | OpenAI | $0.03 / $0.13, cached <$0.01 | <$0.01 | $0.95 |
| Phi 4 | Microsoft | $0.07 / $0.14 | <$0.01 | $1.85 |
| Granite 4.2 8B | IBM | $0.06 / $0.25, cached $0.02 | <$0.01 | $1.87 |
| Nemotron 3.5 Lightning | NVIDIA | $0.07 / $0.20, cached $0.04 | <$0.01 | $1.98 |
| DeepSeek V4.1 Flash | DeepSeek | $0.05 / $0.50, cached <$0.01 | <$0.01 | $2.09 |
| Claude Haiku 5.5 | Anthropic | $0.10 / $0.50, cached $0.01 | <$0.01 | $3.30 |
| GPT-6 Luna | OpenAI | $0.10 / $0.50, cached $0.01 | <$0.01 | $3.30 |
| GPT-6 Luna Pro | OpenAI | $0.10 / $0.50, cached $0.01 | <$0.01 | $3.30 |
| Qwen3.8 Omni Flash | Alibaba (Qwen) | $0.15 / $0.47, cached $0.02 | <$0.01 | $4.33 |
| GLM 5.3 Flash | Zhipu AI (Z.ai) | $0.15 / $0.50, cached $0.02 | $0.01 | $4.40 |
| Nemotron 3.5 Super VL | NVIDIA | $0.15 / $0.50, cached $0.02 | $0.01 | $4.40 |
| Qwen3 Coder Next | Alibaba (Qwen) | $0.12 / $0.80, cached $0.07 | $0.01 | $4.40 |
| GLM 5.3 | Zhipu AI (Z.ai) | $0.07 / $1.40, cached $0.10 | $0.01 | $4.62 |
| DeepSeek V4.1 Flash 1017 | DeepSeek | $0.15 / $0.60, cached <$0.01 | $0.01 | $4.62 |
| MiniMax M3.1 Flash | MiniMax | $0.15 / $0.60, cached <$0.01 | $0.01 | $4.62 |
| Mistral Small 4 | Mistral AI | $0.15 / $0.60, cached $0.02 | $0.01 | $4.62 |
| gpt-oss-120b | OpenAI | $0.15 / $0.60, cached $0.08 | $0.01 | $4.62 |
| Gemma 4 31B | $0.20 / $0.40 | $0.01 | $5.28 | |
| MiniMax M2.7 | MiniMax | $0.21 / $0.84, cached $0.06 | $0.01 | $6.47 |
| DeepSeek V3.2 | DeepSeek | $0.26 / $0.38, cached $0.13 | $0.01 | $6.56 |
| GPT-5.4 Nano | OpenAI | $0.20 / $1.25, cached $0.02 | $0.02 | $7.15 |
| Qwen3.8 27B | Alibaba (Qwen) | $0.15 / $1.88, cached $0.04 | $0.02 | $7.43 |
| MiniMax M2.5 | MiniMax | $0.27 / $0.95, cached $0.03 | $0.02 | $8.03 |
| Gemini 3.1 Flash Lite | $0.25 / $1.50, cached $0.03 | $0.02 | $8.80 | |
| MiniMax M3 | MiniMax | $0.30 / $1.20, cached $0.06 | $0.02 | $9.24 |
| Qwen3.7 Plus | Alibaba (Qwen) | $0.32 / $1.28, cached $0.06 | $0.02 | $9.86 |
| Command A+ | Cohere | $0.30 / $1.50, cached $0.15 | $0.02 | $9.90 |
| Llama 4 Maverick | Meta | $0.35 / $1.00, cached $0.05 | $0.02 | $9.90 |
| GLM 5.3 FlashX | Zhipu AI (Z.ai) | $0.37 / $1.25, cached $0.09 | $0.02 | $10.89 |
| Gemini 2.5 Flash | $0.30 / $2.50, cached $0.03 | $0.03 | $12.10 | |
| GLM 5.2 | Zhipu AI (Z.ai) | <$0.01 / $6.80, cached <$0.01 | $0.03 | $15.09 |
| Nemotron 3 Ultra | NVIDIA | $0.60 / $2.40, cached $0.12 | $0.04 | $18.48 |
| DeepSeek V4 Pro 0813 | DeepSeek | $0.66 / $1.98, cached $0.02 | $0.04 | $18.88 |
| Mistral Large 4 | Mistral AI | $0.70 / $2.10, cached $0.07 | $0.05 | $20.02 |
| Kimi K2.7 Code | Moonshot AI | $0.60 / $3.50, cached $0.15 | $0.05 | $20.90 |
| Kimi K2.6 | Moonshot AI | $0.65 / $3.41, cached $0.15 | $0.05 | $21.80 |
| Gemini 3.6 Flash | $0.75 / $3.75, cached $0.08 | $0.06 | $24.75 | |
| GPT-5.4 Mini | OpenAI | $0.75 / $4.50, cached $0.08 | $0.06 | $26.40 |
| Gemini 3.8 Flash | $0.83 / $4.13, cached $0.08 | $0.06 | $27.23 | |
| Claude Haiku 4.5 | Anthropic | $1.00 / $5.00, cached $0.10 | $0.08 | $33.00 |
| GPT-6.1 Terra | OpenAI | $1.00 / $5.00, cached $0.05 | $0.08 | $33.00 |
| GPT-6.1 Terra Pro | OpenAI | $1.00 / $5.00, cached $0.05 | $0.08 | $33.00 |
| Grok 4.3 | xAI | $1.25 / $2.50, cached $0.20 | $0.08 | $33.00 |
| Muse Spark 1.3 | Meta | $1.25 / $4.25, cached $0.15 | $0.08 | $36.85 |
| Muse Spark Open | Meta | $1.25 / $4.25, cached $0.15 | $0.08 | $36.85 |
| Kimi K3 | Moonshot AI | $0.19 / $16.00, cached $0.18 | $0.09 | $39.42 |
| GLM 5.1 | Zhipu AI (Z.ai) | $1.40 / $4.40, cached $0.26 | $0.09 | $40.48 |
| Qwen3.7 Max | Alibaba (Qwen) | $1.48 / $4.43, cached $0.30 | $0.10 | $42.19 |
| Gemini 2.5 Pro | $1.25 / $10.00, cached $0.13 | $0.11 | $49.50 | |
| Nano Banana 2.1 | $1.50 / $7.50 | $0.11 | $49.50 | |
| Gemini 3.5 Flash | $1.50 / $9.00, cached $0.15 | $0.12 | $52.80 | |
| Grok 4.5 | xAI | $2.00 / $6.00, cached $0.30 | $0.13 | $57.20 |
| Grok 4.6 | xAI | $2.00 / $6.00, cached $0.50 | $0.13 | $57.20 |
| Grok 4.7 | xAI | $2.00 / $6.00, cached $0.50 | $0.13 | $57.20 |
| Qwen3.8 2.4T A95B | Alibaba (Qwen) | $2.00 / $6.00, cached $0.25 | $0.13 | $57.20 |
| Qwen3.8 Max (0902) | Alibaba (Qwen) | $2.00 / $6.00, cached $0.25 | $0.13 | $57.20 |
| GPT-4.1 | OpenAI | $2.00 / $8.00, cached $0.50 | $0.14 | $61.60 |
| o3 | OpenAI | $2.00 / $8.00, cached $0.50 | $0.14 | $61.60 |
| Claude Sonnet 5 | Anthropic | $2.00 / $10.00, cached $0.20 | $0.15 | $66.00 |
| Claude Sonnet 5.5 | Anthropic | $2.00 / $10.00, cached $0.10 | $0.15 | $66.00 |
| GPT-6 Sol | OpenAI | $2.00 / $10.00, cached $0.20 | $0.15 | $66.00 |
| GPT-6 Sol Pro | OpenAI | $2.00 / $10.00, cached $0.20 | $0.15 | $66.00 |
| GPT-6.1 Sol | OpenAI | $2.00 / $10.00, cached $0.10 | $0.15 | $66.00 |
| GPT-6.1 Sol Pro | OpenAI | $2.00 / $10.00, cached $0.10 | $0.15 | $66.00 |
| Gemini 4 Argon | $2.00 / $10.00, cached $0.10 | $0.15 | $66.00 | |
| Kimi K3.1 Pro | Moonshot AI | $2.00 / $10.00, cached $0.20 | $0.15 | $66.00 |
| GPT-5.3-Codex | OpenAI | $1.75 / $14.00, cached $0.18 | $0.16 | $69.30 |
| GPT-5.6 Terra | OpenAI | $2.00 / $12.00, cached $0.20 | $0.16 | $70.40 |
| Gemini 3.1 Pro Preview | $2.00 / $12.00, cached $0.20 | $0.16 | $70.40 | |
| GLM 5.3 Prime | Zhipu AI (Z.ai) | $2.80 / $8.80, cached $0.56 | $0.18 | $80.96 |
| GPT-5.4 | OpenAI | $2.50 / $15.00, cached $0.25 | $0.20 | $88.00 |
| Claude Sonnet 4.6 | Anthropic | $3.00 / $15.00, cached $0.30 | $0.23 | $99.00 |
| Qwen3.8 Max Prime | Alibaba (Qwen) | $4.00 / $12.00, cached $0.50 | $0.26 | $114.40 |
| Claude Opus 5.5 | Anthropic | $4.00 / $20.00, cached $0.20 | $0.30 | $132.00 |
| GPT-5.6 Sol | OpenAI | $4.00 / $20.00, cached $0.40 | $0.30 | $132.00 |
| Muse Wonder | Meta | $4.00 / $20.00, cached $0.20 | $0.30 | $132.00 |
| Claude Opus 4.7 | Anthropic | $5.00 / $25.00, cached $0.50 | $0.38 | $165.00 |
| Claude Opus 4.8 | Anthropic | $5.00 / $25.00, cached $0.50 | $0.38 | $165.00 |
| Claude Opus 5 | Anthropic | $5.00 / $25.00, cached $0.50 | $0.38 | $165.00 |
| GPT-5.5 | OpenAI | $5.00 / $30.00, cached $0.50 | $0.40 | $176.00 |
| Claude Fable 5.1 | Anthropic | $10.00 / $50.00, cached $0.25 | $0.75 | $330.00 |
| GPT-6 Astra | OpenAI | $10.00 / $50.00, cached $1.00 | $0.75 | $330.00 |
| GPT-6 Astra Pro | OpenAI | $10.00 / $50.00, cached $1.00 | $0.75 | $330.00 |
Not sure about token counts? Your provider's usage dashboard or your agent's usage command shows real input and output tokens per session; use those numbers here. Subscriptions can be cheaper for heavy use: compare agent plans, or find an agent with the picker.