Llama 2 7B
llama-2-7bPricing
List prices at Replicate, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.05 | $0.25 |
What it costs a month
At Replicate list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$33.75
- RAG over documents2,000 requests a day, 8K in / 0.6K out$33.00
- Coding agent1,000 requests a day, 40K in / 2K out$75.00
- Overnight batch20,000 requests a day, 4K in / 0.4K out$180
Where to run it
2 hosts serve Llama 2 7B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ReplicateInference llama-2-7b | $0.05 / $0.25 | llama-2-7b | |
Fireworks AIInference llama-v2-7b | $0.20 / $0.20 +100% vs headline | llama-v2-7b |
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 Replicate.
Smaller Meta models
No cheaper Meta model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 5% less
- 10% less
- 13% less
- 3% less
Model line
Newer and older versions, at each lab's own price.
- UndatedLlama 2 7BLatest$0.05 / $0.25
- UndatedLlama2 7BNot listed
Call it
Using Replicate's API.
from litellm import completion
response = completion(
model="replicate/llama-2-7b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 2 7B cost?
On Replicate, Llama 2 7B costs $0.05 per million input tokens and $0.25 per million output tokens.
Which APIs offer Llama 2 7B?
Llama 2 7B runs on 2 APIs: Replicate and Fireworks AI.
What is Llama 2 7B's context window?
4K tokens, with up to 4K tokens in one reply.
Is Llama 2 7B being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama 2 7B?
No. Llama 2 7B is the newest model in its line.
What are cheaper alternatives to Llama 2 7B?
Models that cost less and keep most of what it can do: GLM 5.3 Flash on CLF AI Gateway (5% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 2 7B's API model id?
Use llama-2-7b with Replicate. Other hosts use their own ids: llama-v2-7b on Fireworks AI.
Sources
Raw catalog entry for llama-2-7b on Replicate
{
"input_cost_per_token": 5e-8,
"litellm_provider": "replicate",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 2.5e-7,
"source": "https://replicate.com/meta/llama-2-7b",
"supports_tool_choice": true
}