Model pricing · Meta (via Together AI)
Llama 3.3 70B pricing
Llama 3.3 70B costs $1.04 per million input tokens and $1.04 per million output tokens at list price. Best for: open-weights workhorse.
| Input | $1.04 / 1M tokens |
|---|---|
| Output | $1.04 / 1M tokens |
| Context window | Not published |
Together serverless single rate in/out.
Source: Meta (via Together AI) pricing, cross-checked against models.dev on 2026-09-15. Your provider invoice is authoritative.
What it costs in practice
| Workload | List price |
|---|---|
| One request: 10,000 tokens in, 1,000 out | $0.011 |
| A month of that request, 100 times a day | $34.32 |
| A 3,000-token instruction file on 100 requests a day, for a month | $9.36 |
The last row is the always-on cost of an instruction file like CLAUDE.md: paid on every request, whether the task needs it or not. Check how much of yours is waste.
Price history
From tokencheat's dated pricing snapshots. Only changes are listed.
| Since | Input / 1M | Output / 1M |
|---|---|---|
| 2026-01-01 | $1.04 | $1.04 |
Similarly priced models
Claude Haiku 4.5
$1 in · $5 out · Anthropic
Qwen3-Coder-Plus
$1 in · $5 out · Alibaba
Grok Build 0.1
$1 in · $2 out · xAI
Kimi K2.7 Code
$0.95 in · $4 out · Moonshot AI
Compare every model side by side or price your own workload.