Llama 3.3 70B Instruct
- Input / output
- $0.10 / $0.32
- Providers
- 6
- Spread
- 3.6×
- 7 days
- 0%
- 30 days
- 0%
- Context
- 128K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
| fp8 | $0.10 | $0.32 | $0.155 | −29% | |||
| fp8 | $0.20 | $0.52 | $0.28 | +29% | |||
| fp8 | $0.22 | $0.50 | $0.29 | +33% | |||
| $0.59 | $0.79 | $0.64 | +194% | ||||
| fp16 | $0.71 | $0.71 | $0.71 | +226% | |||
| fp8 | $0.293 | $2.253 | $0.783 | +260% |
- DeepInfraCheapestturbo$0.155$0.10 in · $0.32 out−29% vs ref128K ctx99.4% uptimefp8
- $0.28$0.20 in · $0.52 out+29% vs ref128K ctx99.1% uptimefp8
- $0.29$0.22 in · $0.50 out+33% vs ref128K ctx99.9% uptimefp8
- $0.64$0.59 in · $0.79 out+194% vs ref128K ctx100% uptime
- $0.71$0.71 in · $0.71 out+226% vs ref125K ctx100% uptimefp16
- $0.783$0.293 in · $2.253 out+260% vs ref24K ctx99.4% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.218 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| AkashML | $0.10 |
| Parasail | $0.11 |
| Groq | $0.295 |
| CoreWeave | $0.71 |
Changes
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- PriceDiscount price,25%→——
- PriceOutput price,$0.90→$1.20+33.3%
- PriceInput price,$0.45→$0.60+33.3%
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- DelistedNo longer served,Delisted
- ListedNow served,Listed
About
The cheapest provider for Llama 3.3 70B Instruct is DeepInfra at $0.155 per 1M tokens (blended), charging $0.10 per 1M input and $0.32 per 1M output tokens. 6 providers serve it; the most expensive charges 3.6× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
- Released
- Dec 6, 2024
- First tracked
- Oct 3, 2026
- Canonical slug
- meta-llama/llama-3.3-70b-instruct
- Weights
- meta-llama/Llama-3.3-70B-Instruct