AI Rate Card

Reflection-Llama-3.1-70B · deepinfra

Reflection Llama-3.1 70B is trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course. The model was trained on synthetic data.

Base modelAll models on this baseAll models of the providerto the provider

Input, $/1M $0.35

Output, $/1M $0.40

Limits

  • Every plan: 200 requests at once

Last checked 04.11.2026 12:08:11 UTC Source

Context 8 192

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —

Price alerts

Sign in to follow the price

API

This model type has no common request format: see the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Adeepinfra%7Cmattshumer/Reflection-Llama-3.1-70B, prices checked 2026-11-04

Technical details

ID: offer:deepinfra|mattshumer/Reflection-Llama-3.1-70B