Budget
US$0.20
Qwen2.5 Coder 32B
Qwen (Alibaba)
At a glance
Llama 3.3 70B Instruct from Meta (via aggregator) is a budget model priced at US$0.88 per 1M input tokens and US$0.88 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) Llama 3.3 70B Instruct costs about US$18/month. The 128K-token context window covers single-file workloads comfortably.
What does your monthly budget buy?
Move the slider or switch task mix — values update live.
Monthly budget
US$100 / month
≈ $23/wk · ≈ $4.55/day
on Llama 3.3 70B Instruct
Input tokens
96.6M
Output tokens
17.0M
Total tokens
113.6M
Per month this budget delivers
- Medium feature (10–15 files)420
- PR review3,551
- Lines of TypeScript1,014,610
- Small bug fix3,642
- Work email174,825
- Unit test file3,382
How does this model compare on price?
Input vs output per 1M tokens
Hover a row to compare input vs output rates.
- Llama 3.3 70B InstructUS$0.88US$0.88
- Budget median (other budget models)US$0.30US$1.50
- Cheapest in catalog (Gemini 2.0 Flash)US$0.10US$0.40
Input per 1MOutput per 1M
Cost per task
At the default coding-agent mix.
USD per single task
Hover a bar to see per-task cost detail.
- Lines of TypeScriptUS$0.0001
- Small bug fixUS$0.0275
- PR reviewUS$0.0282
- Read a large docUS$0.0453
- Debug from stack traceUS$0.0589
- Refactor a module (8–12 files)US$0.17
- Medium feature (10–15 files)US$0.24
- Onboard to a new repoUS$0.53
Typical developer day
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$0.24 | US$0.24 | US$5.23 |
| Small bug fix | 5 | US$0.03 | US$0.14 | US$3.02 |
| PR review | 4 | US$0.03 | US$0.11 | US$2.48 |
| Debug from stack trace | 2 | US$0.06 | US$0.12 | US$2.59 |
| Read a large doc | 1 | US$0.05 | US$0.05 | US$1.00 |
| Micro-interaction (explain / lint fix) | 30 | US$0.00 | US$0.03 | US$0.70 |
| Lines of TypeScript | 1,500 | US$0.00 | US$0.15 | US$3.25 |
| Total | US$0.83 | US$18.26 | ||
The 1500-lines-of-TS row models ~1000 lines read (cache-hit) + ~500 lines written. Headline figures are precise to ~5% — see the FAQ.
Monthly cost matrix
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 (≈ $18) | 76 | 648 | 310 | 185,310 |
| $50/month | 210 | 1,775 | 848 | 507,305 |
| $200/month | 841 | 7,102 | 3,394 | 2,029,220 |
| $500/month | 2,104 | 17,755 | 8,486 | 5,073,051 |
| $2000/month | 8,417 | 71,022 | 33,946 | 20,292,207 |
Typical mix: coding-agent (85% input, 50% cache hits). Values show the maximum count of each task type at that budget.
What this model can do
Coding
Trained or post-trained for code generation tasks.
Reasoning
Not supported
Multimodal
Not supported
Prompt cache
Not supported
Batch API
Not supported
Tool use
Native function-calling / tool-use API support.
Long context
Not supported
Extended thinking
Not supported
When does this model fit?
Best for
- Open-weights deployments where data must not leave your network
- Symmetric workloads (equal input and output)
- Fallback model when frontier is rate-limited
Watch out for
- Coding quality clearly below frontier
- No prompt caching on most aggregators
Meta (via aggregator) in the catalog
Total models
1
Median input/1M
US$0.88
Median output/1M
US$0.88
Input range
US$0.88–US$0.88
Related models
Sources
- Together AI Pricing ↗
Verified: 2026-05-07
Frequently asked questions about Llama 3.3 70B Instruct
What does a typical month on Llama 3.3 70B Instruct cost?
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 Llama 3.3 70B Instruct costs about US$18/month. Heavier workloads scale proportionally; lighter workloads cost less.
How big is Llama 3.3 70B Instruct's context window?
128K tokens total, with up to 8K of output. That fits a few dozen source files in a single call.
Why is Llama 3.3 70B Instruct output priced so much higher than input?
Providers charge US$0.88 per 1M output tokens against US$0.88 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.
Does Llama 3.3 70B Instruct support prompt caching?
No. Every input token is billed at the full US$0.88/1M rate. If your workload reuses the same system prompt frequently, compare against a caching-capable model (Claude Sonnet 4.6, GPT-5) where the effective input rate falls sharply.
Try Llama 3.3 70B Instruct pricing live
Open the full calculator with your own budget, task mix and region (US or DE with 19% VAT).
Open calculator