Llama-3.3-70B-Instruct-Turbo API Pricing
Llama-3.3-70B-Instruct-Turbo on Together AI costs $1.04 per 1M input tokens and $1.04 per 1M output tokens (as of ).
| Input | $1.04 / 1M tokens |
|---|---|
| Output | $1.04 / 1M tokens |
| Cached input (read) | — |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 131K tokens |
| Max output | — tokens |
| Supports | tool calling |
| Deprecation date | |
| API model id | meta-llama/Llama-3.3-70B-Instruct-Turbo |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $2.60 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $5.30 |
| 1 million classification calls (300 in, 5 out each) | $317.20 |
Try your own numbers in the LLM API cost calculator.
Price history
- Between and : output price changed from $0.88 to $1.04 per 1M tokens.
- Between and : input price changed from $0.88 to $1.04 per 1M tokens.
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| Kimi-K2.5-fp4 | Together AI | $0.50 | $2.80 | — | 262K |
| GLM-4.6 | Together AI | $0.60 | $2.20 | — | 203K |
| Qwen3.6-Plus | Together AI | $0.50 | $3.00 | — | 1M |
| Qwen2-72B-Instruct | Together AI | $0.90 | $0.90 | — | 33K |
| together-ai-41.1b-80b | Together AI | $0.90 | $0.90 | — | — |
| QwQ-32B | Together AI | $1.20 | $1.20 | — | 131K |
| Qwen2-VL-72B-Instruct | Together AI | $1.20 | $1.20 | — | 33K |
| Qwen2.5-72B-Instruct | Together AI | $1.20 | $1.20 | — | 33K |