Llama 3.1 70B
llama-3.1-70bPricing
List prices at Cerebras, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.60 | $0.60 |
What it costs a month
At Cerebras list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$225
- RAG over documents2,000 requests a day, 8K in / 0.6K out$310
- Coding agent1,000 requests a day, 40K in / 2K out$756
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,584
Where to run it
2 hosts serve Llama 3.1 70B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
CerebrasInference llama-3.1-70b | $0.60 / $0.60 | llama-3.1-70b | |
Vercel AI GatewayGateway llama-3.1-70b | $0.72 / $0.72 +20% vs headline | llama-3.1-70b |
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 Cerebras.
Smaller Meta models
- 79% less
- 67% less
Other frontier labs
- 23% less
- 67% less
- 67% less
- 56% less
Open-weight picks
- 13% less
- 13% less
- 20% less
- 25% less
Model line
Newer and older versions, at each lab's own price.
- UndatedLlama 3.3 70BLatest$0.20 / $0.50
- UndatedLlama3.3 70B$0.72 / $0.72
- UndatedLlama 3.1 70BThis page$0.60 / $0.60
- UndatedLlama3.1 70B$0.72 / $0.72
- UndatedLlama 3 70B$0.59 / $0.79
- UndatedLlama3 70BNot listed
- UndatedLlama 2 70B$0.10 / $0.10
- UndatedLlama2 70BNot listed
Call it
Using Cerebras's API.
from litellm import completion
response = completion(
model="cerebras/llama-3.1-70b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 3.1 70B cost?
On Cerebras, Llama 3.1 70B costs $0.60 per million input tokens and $0.60 per million output tokens.
Which APIs offer Llama 3.1 70B?
Llama 3.1 70B runs on 2 APIs: Cerebras and Vercel AI Gateway.
What is Llama 3.1 70B's context window?
128K tokens, with up to 128K tokens in one reply.
Is Llama 3.1 70B being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama 3.1 70B?
Yes. Llama 3.3 70B is the newest model in this line.
What are cheaper alternatives to Llama 3.1 70B?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (79% less), GPT-5.4 Nano on OpenAI (23% less), Claude Haiku 5.5 on Anthropic (67% less) and DeepSeek Flash on DeepSeek (13% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 3.1 70B's API model id?
Use llama-3.1-70b with Cerebras.
Sources
Raw catalog entry for llama-3.1-70b on Cerebras
{
"input_cost_per_token": 6e-7,
"litellm_provider": "cerebras",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-7,
"supports_function_calling": true,
"supports_tool_choice": true
}