Llama 3.3 70B

llama-3.3-70b-instruct

Pricing

~98%

Input: $0.01452 / 1,000,000 tokens
Output: $0.046464 / 1,000,000 tokens
Cache read: $0.002178 / 1,000,000 tokens
Cache write: $0.01452 / 1,000,000 tokens

How pricing works

Discount history

97.5%Nov 8, 03:56 AM UTC

Nov 7, 11:57 PMNov 8, 03:56 AM UTC

Model details

Input: text
Output: text
Context window: 128,000 tokens
Maximum output: 4,096 tokens
Availability: $7.6KUncapped capacity
Updated: 11/8/2026, 3:58:06 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingTool calling

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p