Llama-2-70b-Chat API pricing

3 providers serve Llama-2-70b-Chat. Llama-2-70b-Chat is a proprietary API model, up to 4K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-08-15 · list prices from provider APIs
Input floor $0.500/1M at Databricks Output floor $1.50/1M at Databricks Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Databricks $0.500 $1.50output floor - 4K Use
Replicate $0.650 $2.75 - 4K Use
Perplexity $0.700 $2.80 - 4K Use

The cheapest way to run Llama-2-70b-Chat

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $80.00/month, at Databricks. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Llama 3.3 70B $0.100 $0.200 15
Llama 3.1 8B $0.020 $0.030 15
Llama 4 Scout $0.050 $0.100 11
Llama 3.1 70B Instruct $0.120 $0.300 10
Llama 4 Maverick $0.050 $0.100 9
Llama 3.2 3B $0.020 $0.020 9

FAQ

What is the cheapest API for Llama-2-70b-Chat?

As of 2026-08-15, the lowest input price for Llama-2-70b-Chat is Databricks at $0.500 per 1M input tokens. The lowest output price is Databricks at $1.50 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Replicate at $0.650, a 30% difference.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON