Text model
meta-llama/Llama-3.2-3B-Instruct pricing
Together AI charges $0.06 per million input tokens and $0.06 per million output tokens for meta-llama/Llama-3.2-3B-Instruct. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.06/ 1M
- Output
- $0.06/ 1M
- Context
- 131.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.06 | $0.06 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000114 | 100,000 | $11.40 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00039 | 100,000 | $39.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.000768 | 250,000 | $192.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with meta-llama/Llama-3.2-3B-Instruct, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| together/Prism-ML/Ternary-Bonsai-27B | $0.00 | 100% |
| deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct | $0.0000931 | 18% |
| cloudflare/@cf/ibm-granite/granite-4.0-h-micro | $0.0000703 | 38% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Together AI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.