Llama2 70B Chat
meta.llama2-70b-chat-v1Pricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.95 | $2.56 |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$777
- RAG over documents2,000 requests a day, 8K in / 0.6K out$1,028
- Coding agent1,000 requests a day, 40K in / 2K out$2,494
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,294
Where to run it
2 hosts serve Llama2 70B Chat. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud meta.llama2-70b-chat-v1 | $1.95 / $2.56 | meta.llama2-70b-chat-v1 | |
SnowflakeCloud llama2-70b-chat | - | llama2-70b-chat |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama Community LicenseRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Amazon Bedrock.
Smaller Meta models
- 5% less
- 94% less
- 90% less
Other frontier labs
- 5% less
- 26% less
- 29% less
- 90% less
Open-weight picks
- 5% less
- 18% less
- 59% less
- 61% less
Model line
Newer and older versions, at each lab's own price.
- UndatedLlama 2 70B ChatLatest$0.90 / $0.90
- UndatedLlama2 70B ChatThis page$1.95 / $2.56
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/meta.llama2-70b-chat-v1",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama2 70B Chat cost?
On Amazon Bedrock, Llama2 70B Chat costs $1.95 per million input tokens and $2.56 per million output tokens.
Which APIs offer Llama2 70B Chat?
Llama2 70B Chat runs on 2 APIs: Amazon Bedrock and Snowflake.
What is Llama2 70B Chat's context window?
4K tokens, with up to 4K tokens in one reply.
Is Llama2 70B Chat being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama2 70B Chat?
Yes. Llama 2 70B Chat is the newest model in this line.
What are cheaper alternatives to Llama2 70B Chat?
Models that cost less and keep most of what it can do: Muse Spark 1.3 on Meta Model API (5% less), GPT-6.1 Terra on OpenAI (5% less), Grok 4.20 Multi Agent on xAI (26% less) and Muse Spark Open on Baseten (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama2 70B Chat's API model id?
Use meta.llama2-70b-chat-v1 with Amazon Bedrock. Other hosts use their own ids: llama2-70b-chat on Snowflake.
Sources
Raw catalog entry for meta.llama2-70b-chat-v1 on Amazon Bedrock
{
"input_cost_per_token": 0.00000195,
"litellm_provider": "bedrock",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.00000256,
"source": "https://aws.amazon.com/bedrock/pricing/"
}