impulse

Llama 2 70B

Open weights
API id llama-v2-70b
Input / 1M
$0.10
at Fireworks AI
Output / 1M
$0.10
at Fireworks AI
Context window
4K
tokens
Max output
4K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at Fireworks AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.10

What it costs a month

At Fireworks AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$37.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$51.60
  • Coding agent1,000 requests a day, 40K in / 2K out$126
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$264
Use your own numbers

Where to run it

2 hosts serve Llama 2 70B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Fireworks AIInference
llama-v2-70b
$0.10 / $0.10
ReplicateInference
llama-2-70b
$0.65 / $2.75
+1075% vs headline

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 License
Runtimes: 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 Fireworks AI.

Smaller Meta models

No cheaper Meta model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • GLM 5.3 Flash
    Zhipu AI · on CLF AI Gateway
    $0.06 / $0.20
    Has every key capability
    5% less
  • Ling 3.0 Flash
    Independent · on DeepInfra
    $0.06 / $0.18
    Has every key capability
    10% less
  • Nemotron 3 Nano 30B A3B
    NVIDIA · on DeepInfra
    $0.05 / $0.20
    Has every key capability
    13% less
  • Granite 4.2 8B
    IBM · on W&B Inference
    $0.06 / $0.15
    Has every key capability
    18% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedLlama 3.3 70BLatest$0.20 / $0.50
  2. UndatedLlama3.3 70B$0.72 / $0.72
  3. UndatedLlama 3.1 70B$0.60 / $0.60
  4. UndatedLlama3.1 70B$0.72 / $0.72
  5. UndatedLlama 3 70B$0.59 / $0.79
  6. UndatedLlama3 70BNot listed
  7. UndatedLlama 2 70BThis page$0.10 / $0.10
  8. UndatedLlama2 70BNot listed

Call it

Using Fireworks AI's API.

Python
from litellm import completion

response = completion(
    model="fireworks_ai/llama-v2-70b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama 2 70B cost?

On Fireworks AI, Llama 2 70B costs $0.10 per million input tokens and $0.10 per million output tokens.

Which APIs offer Llama 2 70B?

Llama 2 70B runs on 2 APIs: Fireworks AI and Replicate.

What is Llama 2 70B's context window?

4K tokens, with up to 4K tokens in one reply.

Is Llama 2 70B being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Llama 2 70B?

Yes. Llama 3.3 70B is the newest model in this line.

What are cheaper alternatives to Llama 2 70B?

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 70B's API model id?

Use llama-v2-70b with Fireworks AI. Other hosts use their own ids: llama-2-70b on Replicate.

Sources

Raw catalog entry for llama-v2-70b on Fireworks AI
{
  "max_input_tokens": 4096,
  "max_output_tokens": 4096,
  "input_cost_per_token": 1e-7,
  "output_cost_per_token": 1e-7,
  "litellm_provider": "fireworks_ai",
  "mode": "chat"
}