LLMLlama 3.3 70B Instruct API pricing
Llama 3.3 70B Instruct by RedPill costs $2.00 per 1M input tokens and $2.00 per 1M output tokens (1M in + 1M out = $4.00).
- API model id
meta-llama/llama-3.3-70b-instruct- Input / 1M
- $2.00
- Output / 1M
- $2.00
- Cached input / 1M
- —
- Context window
- 131K
- Notes
- USD per 1M tokens from RedPill's public models API (pay-as-you-go; the pricing page shows the same per-token rates where both list the model).
- Source
- https://api.redpill.ai/v1/models
- Provider type
- Aggregator (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — RedPill marks this model as TEE-hosted via tinfoil. Inference runs on the named upstream TEE network; RedPill does not document a dedicated EU region.
- Last verified
- 2026-11-12
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| RedPill | Llama 3.3 70B Instruct | $2.50 |
Uses standard list prices (no caching, batch or off-peak discounts). €, CHF and ₹ rows are priced in that currency by the provider and not converted, so compare them with care. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09).
Other RedPill models
- DeepSeek V4 Flash 0731: $0.44 / $1.32
- Kimi K3.1 Pro: $2.00 / $10.00
- GPT-5.6 Sol: $4.00 / $20.00
- GPT-5.6 Terra: $2.00 / $12.00
- Hy3: $0.15 / $0.64
- DeepSeek V4 Pro 0813: $1.45 / $4.36
- Qwen3.8 27B: $0.20 / $2.50
- GLM 5.2: $1.26 / $3.00