How Much Does a Coding Agent Cost per Month?
At production volume (20,000 calls/month), the cheapest effective option is Amazon Nova Micro at $18.26/month. The most expensive frontier option, GPT-5.4 Pro, runs $19,488/month — A coding agent reads large amounts of file context and writes substantial diffs — both sides of the bill are large compared to a chat turn.
How much does coding agent cost per month?
At production volume (20,000 calls/month), the cheapest effective option for coding agent is Amazon Nova Micro at $18.26 per month, verbosity-adjusted rather than list price. The most expensive frontier model, GPT-5.4 Pro, runs $19,488 per month for the same workload.
Token shape
| Shape | large file context in, large diff out |
| Input / output tokens per call | 20K in / 2K out |
| Cacheable input | 60% |
| Batch-eligible | No |
Input is the files and instructions relevant to one change; output is a multi-file diff plus explanation. Repeated reads of the same files across a session make a majority of input cacheable.
Volume
Ranked cost — Production volume
| Model | Provider | List monthly | Effective monthly | Verbosity | Rank Δ |
|---|---|---|---|---|---|
| Amazon Nova Microbudget | Amazon | $19.60 | $10.70 | 0.76× | — |
| Llama 3.1 8Bbudgetlegacy | Groq | $23.20 | $22.46 | 0.77× | — |
| Amazon Nova Litebudget | Amazon | $33.60 | $19.87 | 0.92× | — |
| GPT-5 Nanobudgetlegacy | OpenAI | $36.00 | $25.20 | — | — |
| Gemini 2.5 Flash Litebudgetlegacy | $56.00 | $34.40 | — | ▲1 | |
| GPT-OSS 20Bbudget | Groq | $42.00 | $65.16 | 2.93× | ▼1 |
| Ministral 8Bbudget | Mistral | $66.00 | $65.58 | 0.93× | — |
| Mistral Small 3.1budget | Mistral | $84.00 | $80.40 | 0.85× | ▲4 |
| GPT-4o Minibudgetlegacy | OpenAI | $84.00 | $51.60 | — | — |
| Grok-3 Minibudgetlegacy | xAI | $84.00 | $84.00 | — | — |
| DeepSeek V4 Flashbudget | DeepSeek | $67.20 | $54.88 | 2.60× | ▼3 |
| GPT-OSS 120Bbudget | Groq | $84.00 | $104 | 1.83× | ▼1 |
| Llama 4 Maverickbudgetlegacy | Groq | $104 | $104 | — | — |
| GPT-5.4 Nanobudgetlegacy | OpenAI | $130 | $76.30 | 0.79× | ▲1 |
| GPT-5.6 Lunabudget | OpenAI | $128 | $84.80 | — | ▼1 |
Show all 63 models
| Codestralbudget | Mistral | $156 | $148 | 0.79× | — |
| Gemini 3.1 Flash Litebudgetlegacy | $160 | $98.80 | 0.88× | ▲1 | |
| Gemini 3.5 Flash Litebudget | $160 | $106 | — | ▼1 | |
| GPT-5 Minibudgetlegacy | OpenAI | $180 | $126 | — | ▲1 |
| GPT-OSS 120B (Cerebras)budget | Cerebras | $170 | $210 | 2.33× | ▼1 |
| Gemini 2.5 Flashbudgetlegacy | $220 | $155 | — | ▲1 | |
| Mistral Medium 3budget | Mistral | $240 | $227 | 0.84× | ▲1 |
| Llama 3.3 70Bbudgetlegacy | Groq | $268 | $262 | 0.81× | ▲1 |
| DeepSeek V4 Probudget | DeepSeek | $209 | $195 | 3.31× | ▼3 |
| GLM-5.1midlegacy | Z.ai | $328 | $328 | — | — |
| Qwen 3.8 30Bmid | Groq | $360 | $360 | — | — |
| Qwen 3.6 27Bmidlegacy | Groq | $360 | $360 | — | — |
| Qwen 3.7 Plusmid | Qwen | $400 | $400 | — | — |
| Amazon Nova Promid | Amazon | $448 | $275 | — | — |
| GPT-5.4 Minimidlegacy | OpenAI | $480 | $318 | — | — |
| Gemini 3.1 Flashmidlegacy | $480 | $318 | — | — | |
| Claude Haiku 4.5mid | Anthropic | $600 | $384 | — | ▲1 |
| o3-Minimidlegacy | OpenAI | $616 | $378 | — | ▲1 |
| Grok 4.3mid | xAI | $600 | $642 | 1.42× | ▼2 |
| Qwen 3.8 Maxmid | Qwen | $896 | $896 | — | ▲1 |
| Qwen 3.7 Maxmid | Qwen | $896 | $896 | — | ▲1 |
| GPT-5midlegacy | OpenAI | $900 | $630 | — | ▲1 |
| Grok-3midlegacy | xAI | $960 | $960 | — | ▲1 |
| Gemini 3.6 Flashmid | $960 | $636 | — | ▲1 | |
| Gemini 3.5 Flashmidlegacy | $960 | $636 | — | ▲1 | |
| Grok-4.20 Reasoningmid | xAI | $1,040 | $1,040 | — | ▲2 |
| Grok-4.20mid | xAI | $1,040 | $1,040 | — | ▲2 |
| Mistral Large 3mid | Mistral | $1,040 | $1,040 | — | ▲2 |
| Gemini 3.1 Promid | $1,280 | $670 | 0.63× | ▲4 | |
| GPT-4.1midlegacy | OpenAI | $1,120 | $688 | — | ▲1 |
| GLM-5.2mid | Z.ai | $736 | $1,241 | 3.87× | ▼11 |
| GPT-5.6 Terramid | OpenAI | $1,280 | $848 | — | — |
| GPT-4omidlegacy | OpenAI | $1,400 | $860 | — | ▲1 |
| GPT-5.4midlegacy | OpenAI | $1,600 | $1,060 | — | ▲1 |
| GLM 4.7 (Cerebras)mid | Cerebras | $1,010 | $1,730 | 7.55× | ▼8 |
| Claude Sonnet 4.6mid | Anthropic | $1,800 | $1,152 | — | — |
| Claude Sonnet 4.5midlegacy | Anthropic | $1,800 | $1,152 | — | — |
| Claude Sonnet 4midlegacy | Anthropic | $1,800 | $1,152 | — | — |
| Claude Opus 4.8mid | Anthropic | $3,000 | $1,880 | 0.96× | — |
| Claude Opus 4.7midlegacy | Anthropic | $3,000 | $1,920 | — | — |
| Claude Opus 4.6midlegacy | Anthropic | $3,000 | $1,920 | — | — |
| Claude Opus 4.5midlegacy | Anthropic | $3,000 | $1,920 | — | — |
| GPT-5.6 Solfrontier | OpenAI | $3,200 | $2,120 | — | — |
| GPT-4 Turbofrontierlegacy | OpenAI | $5,200 | $3,040 | — | — |
| Claude Fable 5frontier | Anthropic | $6,000 | $3,840 | — | — |
| Claude Opus 4.1frontierlegacy | Anthropic | $9,000 | $5,760 | — | — |
| Claude Opus 4frontierlegacy | Anthropic | $9,000 | $5,760 | — | — |
| GPT-5.4 Profrontierlegacy | OpenAI | $19,200 | $13,008 | 1.04× | — |
Prompt caching assumes a 90% saving on the cacheable share of input — a stated modelling assumption, providers publish 75-90% off. See the full formula and coverage disclosure →