LLM ReferenceLLM Reference

Llama 2 70B Chat — Available Providers

Last refreshed 2026-05-16. Next refresh: weekly.

Compare pricing and deployment options across 14 providers.

Monthly cost ranking

Ranked for 1M input and 0.2M output tokens per month. Cache and batch discounts are applied only when the provider row has sourced prices.

Traffic profile
US default
14 providers

Provider matrix

Region, SLA, and compliance rows are hidden until curated source fields exist.
Lepton AI API
inference
$0.60
Input / Output$0.50 / $0.50
Serverless
DeepInfra
inference
$0.77
Input / Output$0.64 / $0.64
ServerlessSnippets
Input / Output$0.50 / $1.50
Serverless
Fireworks AI
inference
$1.08
Input / Output$0.90 / $0.90
ServerlessSnippets
Together AI
inference
$1.08
Input / Output$0.90 / $0.90
ServerlessSnippets
Replicate API
marketplace
$1.20
Input / Output$0.65 / $2.75
ServerlessSnippets
GCP Vertex AI
hyperscaler
$1.28
Input / Output$0.80 / $2.40
ServerlessSnippets
$1.89
Input / Output$1.54 / $1.77
ServerlessProvisioned
IBM watsonx
platform
$2.16
Input / Output$1.80 / $1.80
Serverless
AWS Bedrock
hyperscaler
$2.46
Input / Output$1.95 / $2.56
ServerlessSnippets
Not enough pricing
Input / Output- / -
Serverless
NVIDIA NIM
inference
Not enough pricing
Input / Output- / -
Provisioned
Not enough pricing
Input / Output- / -
Serverless
Not enough pricing
Input / Output- / -
Serverless
Llama 2 70B Chat operational data note: this page ranks sourced token, cache, and batch fields only. Region, SLA, compliance, and latency claims are intentionally omitted until a curated matrix is added.