Text model
Qwen/Qwen2-72B-Instruct pricing
Together AI charges $0.90 per million input tokens and $0.90 per million output tokens for Qwen/Qwen2-72B-Instruct. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.90/ 1M
- Output
- $0.90/ 1M
- Context
- 32.8Ktokens
Retired 2025-08-28. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.90 | $0.90 | — | — |
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 | $0.00171 | 100,000 | $171.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00585 | 100,000 | $585.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.01 | 250,000 | $2,880.00 |
| 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 Qwen/Qwen2-72B-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/meta-models/Muse-Glimmer-30B | $0.00112 | 34% |
| together/reflection/Beam-1.0-501B-A23B | $0.00108 | 37% |
| deepinfra/google/gemini-2.5-flash | $0.00145 | 15% |
| google/gemini-2.5-flash | $0.00145 | 15% |
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.