workload

Draft docs and changelogs

Medium input, long output.

Output-heavy work is where cheap output tokens matter most.

Input per request
1.5k
Output per request
1.2k
Requests per month
3,000
Tokens per month
8.1M
Cheapest today
$0.1935
Most expensive
$225

Most of the spread comes from output tokens on this workload. Applying a 60% prompt cache to the cheapest row moves it by $0 a month.

Open this in the calculator

All 21 models at list price, cheapest first.
ModelIn /1MOut /1MPer requestPer monthShareBuy
Mistral NemoMistralcheapestopen weights$0.019$0.030$0.000065$0.1935Open
GPT-OSS 20BOpenAIopen weights$0.018$0.090$0.000135$0.405Openaff
Llama 3.1 8BMetaopen weights$0.050$0.080$0.000171$0.513Openaff
Qwen3.7 FlashAlibaba$0.030$0.130$0.000201$0.603Open
DeepSeek V4 FlashDeepSeek$0.086$0.171$0.000334$1.00Open
Gemini 2.5 Flash-LiteGoogle$0.100$0.400$0.00063$1.89Open
GLM 5.3 FlashZ.ai$0.150$0.500$0.000825$2.47Open
Grok 4.3xAI$1.25$2.50$0.0049$14.62Open
Gemini 3.8 FlashGoogle$0.750$3.75$0.0056$16.88Open
Claude Haiku 4.5Anthropic$1.00$5.00$0.0075$22.50Openaff
Grok 4.6xAI$2.00$6.00$0.0102$30.60Open
GPT-5.1OpenAI$1.25$10.00$0.0139$41.62Open
Claude Sonnet 5Anthropic$2.00$10.00$0.015$45.00Openaff
Gemini 3.1 ProGoogle$2.00$12.00$0.0174$52.20Open
GPT-5.2 CodexOpenAI$1.75$14.00$0.0194$58.28Open
GPT-5.4OpenAI$2.50$15.00$0.0218$65.25Open
Kimi K3Moonshot$3.00$15.00$0.0225$67.50Open
Claude Opus 5.5Anthropic$4.00$20.00$0.030$90.00Openaff
GPT-5.5OpenAI$5.00$30.00$0.0435$131Open
Claude Fable 5.1Anthropic$10.00$50.00$0.075$225Openaff
GPT-6 AstraOpenAI$10.00$50.00$0.075$225Open

Other workloads

Figures assume no retries, no failed calls, and no tool-use tokens. How the arithmetic works.

Prices read from 6 provider pricing pages on Sep 24, 2026. Some outbound links may be affiliate links. How that works.