PPLX 70B Online
pplx-70b-onlinePricing
List prices at Perplexity, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.00 | $2.80 |
What it costs a month
At Perplexity list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$210
- RAG over documents2,000 requests a day, 8K in / 0.6K out$101
- Coding agent1,000 requests a day, 40K in / 2K out$168
- Overnight batch20,000 requests a day, 4K in / 0.4K out$672
Where to run it
1 host serve PPLX 70B Online. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
PerplexityGateway pplx-70b-online | $0.00 / $2.80 | pplx-70b-online |
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
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 Perplexity.
Smaller Perplexity models
- 36% less
- 83% less
- 83% less
Other frontier labs
- 34% less
- 71% less
- 71% less
- 63% less
Open-weight picks
- 2% less
- 9% less
- 25% less
- 31% less
Call it
Using Perplexity's API.
from litellm import completion
response = completion(
model="perplexity/pplx-70b-online",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does PPLX 70B Online cost?
On Perplexity, PPLX 70B Online costs $2.80 per million output tokens.
Which APIs offer PPLX 70B Online?
PPLX 70B Online runs on 1 API: Perplexity.
What is PPLX 70B Online's context window?
4K tokens, with up to 4K tokens in one reply.
Is PPLX 70B Online being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to PPLX 70B Online?
Models that cost less and keep most of what it can do: Sonar Medium Online on Perplexity (36% less), GPT-5.4 Nano on OpenAI (34% less), Claude Haiku 5.5 on Anthropic (71% less) and Kimi K2.7 Code on CLF AI Gateway (2% less). Savings are on a mix of 3 input tokens to 1 output token.
What is PPLX 70B Online's API model id?
Use pplx-70b-online with Perplexity.
Sources
Raw catalog entry for pplx-70b-online on Perplexity
{
"input_cost_per_request": 0.005,
"input_cost_per_token": 0,
"litellm_provider": "perplexity",
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.0000028
}