Frontier
US$3.00
Grok 4
xAI
xAI · Budget · US$0.20 input/1M · US$1.50 output/1M · 256K context
Typical monthly cost
US$5.27
≈ per day
US$0.24
Blended cost/1M
US$0.33
Context window
256K
Grok Code Fast 1 from xAI is a budget model priced at US$0.20 per 1M input tokens and US$1.50 per 1M output tokens. For a typical solo-developer workload (8 hours/day, 22 days/month — 1 medium feature, 5 small bug fixes, 4 PR reviews, 2 stack-trace debugs, ~1500 lines of TypeScript, 1 large-doc read, with prompt caching at the default mix) Grok Code Fast 1 costs about US$5/month. The 256K-token context window covers most monorepo scans without truncation.
Move the slider or switch task mix — values update live.
Monthly budget
US$100 / month
≈ $23/wk · ≈ $4.55/day
on Grok Code Fast 1
Input tokens
680.0M
Output tokens
10.0M
Total tokens
690.0M
Per month this budget delivers
At the default coding-agent mix with 50% cache hits.
The 22-day month is based on the median working-day count across DE/US.
| Activity | Count | Per task | Daily | Monthly |
|---|---|---|---|---|
| Medium feature (10–15 files) | 1 | US$0.10 | US$0.10 | US$2.10 |
| Small bug fix | 5 | US$0.01 | US$0.03 | US$0.61 |
| PR review | 4 | US$0.01 | US$0.03 | US$0.59 |
| Debug from stack trace | 2 | US$0.01 | US$0.02 | US$0.49 |
| Read a large doc | 1 | US$0.01 | US$0.01 | US$0.19 |
| Micro-interaction (explain / lint fix) | 30 | US$0.00 | US$0.01 | US$0.28 |
| Lines of TypeScript | 1,500 | US$0.00 | US$0.05 | US$1.01 |
| Total | US$0.24 | US$5.27 | ||
The 1500-lines-of-TS row models ~1000 lines read (cache-hit) + ~500 lines written. Headline figures are precise to ~5% — see the FAQ.
What each monthly budget buys on this model (typical solo-developer day, 22 working days).
| Monthly budget | Medium features | PR reviews | Debug sessions | Lines of TS |
|---|---|---|---|---|
| Typical (≈ $5) | 55 | 780 | 476 | 172,736 |
| $50/month | 522 | 7,407 | 4,524 | 1,639,344 |
| $200/month | 2,091 | 29,629 | 18,099 | 6,557,377 |
| $500/month | 5,228 | 74,074 | 45,248 | 16,393,442 |
| $2000/month | 20,915 | 296,296 | 180,995 | 65,573,770 |
Typical mix: coding-agent (85% input, 50% cache hits). Values show the maximum count of each task type at that budget.
Coding
Trained or post-trained for code generation tasks.
Reasoning
Not supported
Multimodal
Not supported
Prompt cache
Cache reads billed at ~10% of input price — cuts agent costs sharply.
Batch API
Not supported
Tool use
Native function-calling / tool-use API support.
Long context
≥ 200K-token context window.
Extended thinking
Not supported
Total models
2
Median input/1M
US$1.60
Median output/1M
US$8.25
Input range
US$0.20–US$3.00
Verified: 2026-05-07
Running the realistic solo-developer day (1 medium feature + 5 small bug fixes + 4 PR reviews + 2 debug sessions + ~1500 lines of TypeScript + 1 large-doc read, 22 working days) on Grok Code Fast 1 costs about US$5/month. Heavier workloads scale proportionally; lighter workloads cost less.
256K tokens total, with up to 16K of output. That fits whole repository snapshots, tests included in a single call.
Providers charge US$1.50 per 1M output tokens against US$0.20 per 1M input — output requires real compute, input comes mostly from cache. Coding agents read many files (input-heavy) and emit compact diffs (low output), so total spend is usually input-driven.
Cache reads typically cost only 10% of the regular input rate. On a coding-agent mix with 50% cache hits, that saves roughly 45% on input — which is about 38% off your total bill on input-heavy workloads. Anthropic models charge a one-time cache-write surcharge (25% over input) that pays for itself after 2–3 hits.
Open the full calculator with your own budget, task mix and region (US or DE with 19% VAT).
Open calculator