Translating content across languages. Token counts vary by language — CJK scripts tokenize differently from Latin scripts, which changes cost per word.
Input / request
5,000
Output / request
5,500
Cacheable input
15%
Requests / user / day
15
Cost by model
| Model | Per request | Per user / month | 500 users / month | vs cheapest |
|---|---|---|---|---|
| bestGLM-4.7-Flash (Z.ai) | Free | Free | Free | — |
| GLM-4.5-Flash (Z.ai) | Free | Free | Free | Not comparable |
| GLM-4.6V-Flash (Z.ai) | Free | Free | Free | Not comparable |
| OpenRouter Free Tier (Llama 3.3) | Free | Free | Free | Not comparable |
| Ox Alpha (Z.ai GLM preview) | Free | Free | Free | Not comparable |
| Text Embedding 3 (Small) | $0.0001 | $0.045 | $22.50 | Not comparable |
| Text Embedding 004 | $0.0001 | $0.045 | $22.50 | Not comparable |
| Llama 3.2 3B Instruct | $0.000425 | $0.1913 | $95.625 | Not comparable |
| Text Embedding 3 (Large) | $0.00065 | $0.2925 | $146.25 | Not comparable |
| Llama 3.1 8B Instruct | $0.00069 | $0.3105 | $155.25 | Not comparable |
| Groq LPU — Llama 3.1 8B Instant | $0.00069 | $0.3105 | $155.25 | Not comparable |
| Amazon Nova Micro | $0.000925 | $0.4164 | $208.195 | Not comparable |
| GLM-4-32B-0414-128K (Z.ai) | $0.00105 | $0.4725 | $236.25 | Not comparable |
| Cohere Command R7B | $0.001075 | $0.4838 | $241.875 | Not comparable |
| Llama 3.2 1B Instruct (OpenRouter) | $0.00124 | $0.5582 | $279.113 | Not comparable |
| Qwen 2.5 Turbo | $0.001316 | $0.5923 | $296.156 | Not comparable |
| Together AI — GPT-OSS-20B | $0.00135 | $0.6075 | $303.75 | Not comparable |
| Yi-Lightning (01.AI) | $0.00147 | $0.6615 | $330.75 | Not comparable |
| Ministral 3 8B | $0.001474 | $0.6632 | $331.594 | Not comparable |
| Mistral Small 3.2 24B (OpenRouter) | $0.001475 | $0.6638 | $331.875 | Not comparable |
| Amazon Nova Lite | $0.001586 | $0.7138 | $356.906 | Not comparable |
| Muse Spark 1.2 Contributor (OpenRouter) | $0.0016 | $0.72 | $360.00 | Not comparable |
| Llama 3.2 11B Vision | $0.00168 | $0.756 | $378.00 | Not comparable |
| GLM-5.3-Flash (Z.ai) | $0.001705 | $0.7673 | $383.625 | Not comparable |
| DeepInfra — Qwen 2.5 Coder 32B | $0.00172 | $0.774 | $387.00 | Not comparable |
| Ministral 3 14B | $0.001965 | $0.8843 | $442.125 | Not comparable |
| Gemini 2.0 Flash-Lite | $0.001983 | $0.8923 | $446.133 | Not comparable |
| Gemini 1.5 Flash | $0.001983 | $0.8923 | $446.133 | Not comparable |
| Hy-MT2-30B-A3B (OpenRouter) | $0.001993 | $0.8966 | $448.313 | Not comparable |
| Gemma 2 9B Instruct | $0.0021 | $0.945 | $472.50 | Not comparable |
| DeepSeek V3 (Chat) | $0.002146 | $0.9655 | $482.738 | Not comparable |
| DeepSeek Coder V2.5 | $0.002146 | $0.9655 | $482.738 | Not comparable |
| Microsoft Phi-4 (14B) | $0.00215 | $0.9675 | $483.75 | Not comparable |
| DeepInfra — Llama 3.3 70B | $0.00215 | $0.9675 | $483.75 | Not comparable |
| GLM-4.6V-FlashX (Z.ai) | $0.002373 | $1.068 | $533.925 | Not comparable |
| Groq LPU — Llama 4 Scout | $0.002379 | $1.07 | $535.219 | Not comparable |
| GLM-4.7-FlashX (Z.ai) | $0.002505 | $1.127 | $563.625 | Not comparable |
| Fireworks AI — Llama 4 Scout | $0.002513 | $1.131 | $565.313 | Not comparable |
| Gemini 2.5 Flash-Lite | $0.002644 | $1.19 | $594.844 | Not comparable |
| Gemini 2.0 Flash | $0.002644 | $1.19 | $594.844 | Not comparable |
| AI21 Jamba 1.5 Mini | $0.0032 | $1.44 | $720.00 | Not comparable |
| Llama 4 Scout (109B MoE) | $0.003225 | $1.451 | $725.625 | Not comparable |
| DeepSeek V3.2 (OpenRouter) | $0.003293 | $1.482 | $740.813 | Not comparable |
| Qwen3.8-Flash (QwenCloud preview) | $0.003385 | $1.523 | $761.625 | Not comparable |
| Groq LPU — QwQ 32B Reasoner | $0.003595 | $1.618 | $808.875 | Not comparable |
| Grok 4.1 Fast | $0.00363 | $1.634 | $816.75 | Not comparable |
| Mistral Small 4 | $0.003949 | $1.777 | $888.469 | Not comparable |
| GPT-4o mini | $0.003994 | $1.797 | $898.594 | Not comparable |
| Cohere Command R | $0.00405 | $1.823 | $911.25 | Not comparable |
| Microsoft Phi-3.5 MoE | $0.00405 | $1.823 | $911.25 | Not comparable |
| Llama 3.3 70B Instruct | $0.004145 | $1.865 | $932.625 | Not comparable |
| Qwen 2.5 Coder 32B | $0.004165 | $1.874 | $937.125 | Not comparable |
| Llama 3.1 70B Instruct (OpenRouter) | $0.0042 | $1.89 | $945.00 | Not comparable |
| Groq LPU — Llama 4 Maverick | $0.004225 | $1.901 | $950.625 | Not comparable |
| Qwen3 Coder Next (OpenRouter) | $0.004963 | $2.233 | $1,116.563 | Not comparable |
| Qwen 2.5 72B Instruct | $0.005364 | $2.414 | $1,206.844 | Not comparable |
| Gemma 4 31B Instruct | $0.005375 | $2.419 | $1,209.375 | Not comparable |
| NVIDIA Llama 3.1 Nemotron 70B | $0.0056 | $2.52 | $1,260.00 | Not comparable |
| Cerebras — GPT OSS 120B | $0.005875 | $2.644 | $1,321.875 | Not comparable |
| Qwen 3 32B Instruct | $0.00613 | $2.759 | $1,379.25 | Not comparable |
| Qwen3 Coder Flash (OpenRouter) | $0.00622 | $2.799 | $1,399.613 | Not comparable |
| Codestral 2501 | $0.006248 | $2.811 | $1,405.688 | Not comparable |
| Codestral 2508 (OpenRouter) | $0.006248 | $2.811 | $1,405.688 | Not comparable |
| GLM-4.6V (Z.ai) | $0.006263 | $2.818 | $1,409.062 | Not comparable |
| Cerebras — Qwen 3 32B | $0.0064 | $2.88 | $1,440.00 | Not comparable |
| Together AI — Llama 4 Maverick | $0.0067 | $3.015 | $1,507.50 | Not comparable |
| GLM-4.5-Air (Z.ai) | $0.006923 | $3.115 | $1,557.563 | Not comparable |
| MiniMax-01 (4M Context) | $0.00693 | $3.118 | $1,559.25 | Not comparable |
| Groq LPU — Llama 3.3 70B | $0.007295 | $3.283 | $1,641.375 | Not comparable |
| GPT-5.6 Luna | $0.007465 | $3.359 | $1,679.625 | Not comparable |
| GPT-5.6 Luna Pro (OpenRouter) | $0.007465 | $3.359 | $1,679.625 | Not comparable |
| GPT-5.4 nano | $0.00774 | $3.483 | $1,741.50 | Not comparable |
| MiniMax M2.7 (OpenRouter) | $0.00792 | $3.564 | $1,782.00 | Not comparable |
| MiniMax M3 (OpenRouter) | $0.00792 | $3.564 | $1,782.00 | Not comparable |
| Claude 3 Haiku | $0.007956 | $3.58 | $1,790.156 | Not comparable |
| QwQ 32B (Reasoner) | $0.00833 | $3.748 | $1,874.25 | Not comparable |
| Llama 4 Maverick (400B MoE) | $0.009125 | $4.106 | $2,053.125 | Not comparable |
| DeepSeek V4 Flash | $0.009141 | $4.113 | $2,056.613 | Not comparable |
| DeepSeek V4 Flash Vision Exp | $0.009141 | $4.113 | $2,056.613 | Not comparable |
| Gemini 3.1 Flash Lite (OpenRouter) | $0.009331 | $4.199 | $2,099.531 | Not comparable |
| Llama 3.2 90B Vision | $0.00945 | $4.253 | $2,126.25 | Not comparable |
| Mistral Large 3 | $0.0104 | $4.686 | $2,342.813 | Not comparable |
| Perplexity Sonar | $0.0105 | $4.725 | $2,362.50 | Not comparable |
| GPT-3.5 Turbo | $0.0108 | $4.838 | $2,418.75 | Not comparable |
| Together AI — DeepSeek V4 | $0.0108 | $4.838 | $2,418.75 | Not comparable |
| GLM-4.5V (Z.ai) | $0.0125 | $5.64 | $2,819.813 | Not comparable |
| Databricks DBRX Instruct | $0.0129 | $5.805 | $2,902.50 | Not comparable |
| Cerebras — Gemma 4 31B | $0.0131 | $5.915 | $2,957.625 | Not comparable |
| Devstral 2 (2512) (OpenRouter) | $0.014 | $6.301 | $3,150.675 | Not comparable |
| DeepSeek R1 (Reasoner) | $0.0145 | $6.519 | $3,259.687 | Not comparable |
| GLM-4.6 (Z.ai) | $0.0147 | $6.63 | $3,314.813 | Not comparable |
| GLM-4.5 (Z.ai) | $0.0147 | $6.63 | $3,314.813 | Not comparable |
| GLM 4.7 (Zhipu) | $0.0147 | $6.63 | $3,314.813 | Not comparable |
| Fireworks AI — DeepSeek R1 | $0.0148 | $6.658 | $3,328.875 | Not comparable |
| Qwen3.5 397B A17B (OpenRouter) | $0.0148 | $6.669 | $3,334.50 | Not comparable |
| Gemini 3.5 Flash-Lite | $0.015 | $6.771 | $3,385.687 | Not comparable |
| Gemini 2.5 Flash | $0.0151 | $6.787 | $3,393.281 | Not comparable |
| Grok Build 0.1 | $0.0154 | $6.93 | $3,465.00 | Not comparable |
| Qwen3.8 27B (OpenRouter) | $0.0186 | $8.37 | $4,185.00 | Not comparable |
| Grok 4.3 | $0.0192 | $8.646 | $4,322.813 | Not comparable |
| Amazon Nova Pro | $0.0212 | $9.518 | $4,758.75 | Not comparable |
| OpenRouter Auto-Best Router | $0.0215 | $9.675 | $4,837.50 | Not comparable |
| Kimi K2.7 Code (OpenRouter) | $0.0217 | $9.76 | $4,880.25 | Not comparable |
| GLM-5 (Z.ai) | $0.022 | $9.90 | $4,950.00 | Not comparable |
| NVIDIA Nemotron-4 340B | $0.024 | $10.80 | $5,400.00 | Not comparable |
| Qwen3 VL 235B Thinking (OpenRouter) | $0.024 | $10.80 | $5,400.00 | Not comparable |
| Claude 3.5 Haiku | $0.0255 | $11.457 | $5,728.50 | Not comparable |
| GLM-5-Turbo (Z.ai) | $0.0273 | $12.276 | $6,138.00 | Not comparable |
| GLM-5V-Turbo (Z.ai) | $0.0273 | $12.276 | $6,138.00 | Not comparable |
| DeepSeek V4 Pro | $0.0274 | $12.34 | $6,170.175 | Not comparable |
| GPT-5.4 mini | $0.028 | $12.597 | $6,298.594 | Not comparable |
| Llama 3.1 405B Instruct | $0.028 | $12.60 | $6,300.00 | Not comparable |
| o4-mini | $0.0291 | $13.087 | $6,543.281 | Not comparable |
| o3-mini | $0.0293 | $13.179 | $6,589.688 | Not comparable |
| o1-mini | $0.0293 | $13.179 | $6,589.688 | Not comparable |
| GLM-4.5-AirX (Z.ai) | $0.0296 | $13.315 | $6,657.75 | Not comparable |
| GLM-5.3 (Z.ai) | $0.0303 | $13.655 | $6,827.625 | Not comparable |
| GLM-5.2 (Z.ai) | $0.0303 | $13.655 | $6,827.625 | Not comparable |
| GLM-5.1 (Z.ai) | $0.0303 | $13.655 | $6,827.625 | Not comparable |
| Claude Haiku 4.5 | $0.0318 | $14.321 | $7,160.625 | Not comparable |
| Gemini 1.5 Pro | $0.033 | $14.871 | $7,435.547 | Not comparable |
| Gemini 3.7 Flash | $0.0395 | $17.769 | $8,884.688 | Not comparable |
| Kimi K2.6 | $0.0395 | $17.769 | $8,884.688 | Not comparable |
| Pixtral Large | $0.0417 | $18.743 | $9,371.25 | Not comparable |
| Mistral Large 2 (2411) | $0.0417 | $18.743 | $9,371.25 | Not comparable |
| Qwen 3.8 Max (2.4T MoE) | $0.0417 | $18.743 | $9,371.25 | Not comparable |
| Grok 4.5 | $0.0417 | $18.776 | $9,388.125 | Not comparable |
| Grok 4.6 Flagship | $0.0419 | $18.844 | $9,421.875 | Not comparable |
| Qwen 2.5 Max | $0.0421 | $18.954 | $9,477.00 | Not comparable |
| Gemini 3.6 Flash | $0.0477 | $21.482 | $10,740.938 | Not comparable |
| Mistral Medium 3.5 | $0.0477 | $21.482 | $10,740.938 | Not comparable |
| Amazon Nova Premier | $0.0527 | $23.693 | $11,846.25 | Not comparable |
| Perplexity Sonar Reasoning Pro | $0.054 | $24.30 | $12,150.00 | Not comparable |
| Perplexity Sonar Deep Research | $0.054 | $24.30 | $12,150.00 | Not comparable |
| AI21 Jamba 1.5 Large | $0.054 | $24.30 | $12,150.00 | Not comparable |
| Gemini 3.5 Flash (OpenRouter) | $0.056 | $25.194 | $12,597.187 | Not comparable |
| GLM-4.5-X (Z.ai) | $0.0586 | $26.387 | $13,193.438 | Not comparable |
| Gemini 2.5 Pro | $0.0605 | $27.246 | $13,623.047 | Not comparable |
| Claude Sonnet 5 | $0.0637 | $28.643 | $14,321.25 | Not comparable |
| GPT-5.6 Sol Pro (OpenRouter) | $0.0637 | $28.643 | $14,321.25 | Not comparable |
| Grok 2 | $0.065 | $29.25 | $14,625.00 | Not comparable |
| Grok 2 Vision | $0.065 | $29.25 | $14,625.00 | Not comparable |
| Cohere Command A+ | $0.0658 | $29.616 | $14,807.812 | Not comparable |
| GPT-4o (Omni) | $0.0666 | $29.953 | $14,976.563 | Not comparable |
| Cohere Command R+ | $0.0675 | $30.375 | $15,187.50 | Not comparable |
| GPT-5.6 Terra | $0.0747 | $33.593 | $16,796.25 | Not comparable |
| Gemini 3.1 Pro | $0.0747 | $33.593 | $16,796.25 | Not comparable |
| GPT-5.6 Terra Pro (OpenRouter) | $0.0747 | $33.593 | $16,796.25 | Not comparable |
| GPT-5.3 Codex | $0.0846 | $38.056 | $19,027.969 | Not comparable |
| GPT-5.4 Workhorse | $0.0933 | $41.991 | $20,995.312 | Not comparable |
| Claude 3.7 Sonnet (Hybrid Reasoning) | $0.0955 | $42.964 | $21,481.875 | Not comparable |
| Claude 3.5 Sonnet | $0.0955 | $42.964 | $21,481.875 | Not comparable |
| Kimi K3 (Moonshot) | $0.0955 | $42.964 | $21,481.875 | Not comparable |
| Claude Sonnet 4.6 (OpenRouter) | $0.0955 | $42.964 | $21,481.875 | Not comparable |
| Perplexity Sonar Pro | $0.0975 | $43.875 | $21,937.50 | Not comparable |
| Claude Opus 5 | $0.1591 | $71.606 | $35,803.125 | Not comparable |
| Claude Opus 4.8 (OpenRouter) | $0.1591 | $71.606 | $35,803.125 | Not comparable |
| GPT-5.6 Sol | $0.1866 | $83.981 | $41,990.625 | Not comparable |
| GPT-5.5 Standard | $0.1866 | $83.981 | $41,990.625 | Not comparable |
| GPT-4 Turbo | $0.2113 | $95.063 | $47,531.25 | Not comparable |
| o3 (Reasoning Frontier) | $0.2633 | $118.462 | $59,231.25 | Not comparable |
| Claude Fable 5 | $0.3182 | $143.212 | $71,606.25 | Not comparable |
| o1 (Reasoning) | $0.3994 | $179.719 | $89,859.375 | Not comparable |
| GPT-5.6 Cyber | $0.4666 | $209.953 | $104,976.563 | Not comparable |
| Claude 3 Opus | $0.4774 | $214.819 | $107,409.375 | Not comparable |
| o3-pro (Frontier Reasoning) | $0.5265 | $236.925 | $118,462.50 | Not comparable |
| GPT-5.5 Pro | $1.12 | $503.888 | $251,943.75 | Not comparable |
Assumes the typical cacheable share (15% of input at cached rates where published). 15 requests/user/day. Adjust everything in the monthly calculator.
Best value picks for Translation
| Model | Fit score | Cost / 1K requests | Value (fit ÷ cost) |
|---|---|---|---|
| best valueGLM-5.3-Flash (Z.ai) | 59.0 | $1.705 | 34.6 |
| DeepSeek V3.2 (OpenRouter) | 44.2 | $3.293 | 13.4 |
| Llama 3.1 8B Instruct | 5.4 | $0.69 | 7.8 |
| GPT-5.6 Luna | 53.1 | $7.465 | 7.1 |
| DeepSeek V3 (Chat) | 13.1 | $2.146 | 6.1 |
Fit = weighted blend of third-party composite indices (intelligence, coding, agentic) for this use case; value = fit ÷ cost per 1,000 requests. Models without a verified composite are excluded. Methodology · Benchmark hub.
How to spend less
Related workflow costs
FAQ
Using a typical profile of 5,000 input and 5,500 output tokens with 15% cacheable input: from Free on GLM-4.7-Flash (Z.ai) up to $1.12 on GPT-5.5 Pro. See the table for every model.
At 15 requests per user per day and the typical token profile, budget from Free per active user per month on GLM-4.7-Flash (Z.ai). A team of 500 active users lands around Free/month at that tier. Model your exact numbers in the monthly cost calculator.
Output length ≈ input length; budget both sides of the request. Japanese and Chinese text typically costs more per word than English due to tokenization. Cache translation memories and glossaries embedded in the prompt.