Llama-3.1-Nemotron-70B-Instruct API Pricing
Llama-3.1-Nemotron-70B-Instruct on DeepInfra costs $0.60 per 1M input tokens and $0.60 per 1M output tokens (as of ).
| Input | $0.60 / 1M tokens |
|---|---|
| Output | $0.60 / 1M tokens |
| Cached input (read) | — |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 131K tokens |
| Max output | 131K tokens |
| Supports | tool calling |
| Deprecation date | None listed |
| API model id | nvidia/Llama-3.1-Nemotron-70B-Instruct |
| 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) | $1.50 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $3.06 |
| 1 million classification calls (300 in, 5 out each) | $183.00 |
Try your own numbers in the LLM API cost calculator.
Price history
No price change recorded since .
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| olmOCR-7B-0725-FP8 | DeepInfra | $0.27 | $1.50 | — | 16K |
| gemini-3.1-flash-lite | DeepInfra | $0.25 | $1.50 | — | 1M |
| Inkling-Small | DeepInfra | $0.45 | $1.20 | $0.10 | 524K |
| L3.3-70B-Euryale-v2.3 | DeepInfra | $0.65 | $0.75 | — | 131K |
| Muse-Glimmer-30B | DeepInfra | $0.30 | $1.20 | $0.04 | 131K |
| Seed-1.8 | DeepInfra | $0.25 | $2.00 | $0.05 | 256K |
| Hermes-3-Llama-3.1-70B | DeepInfra | $0.70 | $0.70 | — | 131K |
| Qwen3-Coder-480B-A35B-Instruct | DeepInfra | $0.40 | $1.60 | — | 262K |