DeepInfra

meta-llama/Llama-3.3-70B-Instruct-Turbo

$0.1 in · $0.32 out per million tokens · 131,072 tokens of context · first token in 2,169 ms

Get an API key

Price, limits and measured speed

Input price
$0.1 per million tokens
gateway.plungeai.com
Output price
$0.32 per million tokens
gateway.plungeai.com
DeepInfra's list price, input
$0.1 per million tokens
DeepInfra's list price, as our price feed records it
DeepInfra's list price, output
$0.32 per million tokens
DeepInfra's list price, as our price feed records it
Against the list price
At the list price
gateway.plungeai.com
Context window
131,072 tokens
gateway.plungeai.com
Tool calling
Yes
gateway.plungeai.com
Reads images
No
gateway.plungeai.com
Streams its answer
Yes
gateway.plungeai.com
Served by
DeepInfra
gateway.plungeai.com
Time to first token
2,169 ms
our probe of 22 November 2026 · measured by us
Output speed
9.2 tokens a second
our probe of 22 November 2026 · measured by us
Price of our test call
$0.000042
our probe of 22 November 2026, as the API stated it · measured by us
Input price rank
8th lowest of 55 chat models
the models on this site we could call · measured by us
Output price rank
5th lowest of 55
the models on this site we could call · measured by us
First-token rank
47th fastest of 55 measured
our probe of 22 November 2026 · measured by us
Output speed rank
41st fastest of 42 measured
our probe of 22 November 2026 · measured by us
Context rank
40th largest of 55
the models on this site we could call · measured by us

Call it

curl

curl https://api.plungeai.com/v1/chat/completions \
  -H "Authorization: Bearer $PLUNGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

What it costs for three jobs

The same three jobs on every model page, so two models can be compared.

The cost of three reference workloads on deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo
JobTokens inTokens outThrough One APIAt DeepInfra's list price
A chat turn1,000300$0.000196$0.000196
An answer over retrieved documents8,000500$0.00096$0.00096
A summary of a long document100,0002,000$0.0106$0.0106

Models near it

Each against meta-llama/Llama-3.3-70B-Instruct-Turbo: its input price and the time to its first token.

Models related to deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo by provider, price and context
ModelWhy it is hereInput price against itFirst token against itInput, $ per 1MOutput, $ per 1MContext, tokensFirst tokenTokens a second
deepinfra/openai/gpt-oss-120bSame provider−63 %−977 ms$0.037$0.17131,0721,192 ms11.1
deepinfra/deepseek-ai/DeepSeek-V4.1-FlashSame provider+100 %−1,680 ms$0.2$0.61,048,576489 ms202.3
groq/openai/gpt-oss-20bCheaper, same abilities−25 %−1,810 ms$0.075$0.3131,072359 msnot measured
google/gemma-4-26b-a4b-itCheaper, same abilities−32 %−1,187 ms$0.0675$0.225262,144982 msnot measured
anthropic/claude-haiku-5-5Larger contextthe same−1,156 ms$0.1$0.51,000,0001,013 ms749.2

What changed

Every change

In short

  • One API charges DeepInfra's list price for meta-llama/Llama-3.3-70B-Instruct-Turbo: $0.1 in and $0.32 out per million tokens.
  • By input price it is the 8th lowest of the 55 chat models we could call on 22 November 2026.
  • Its first token arrived after 2,169 ms in our test; the median of the 3 DeepInfra models we called was 1,192 ms.
  • Its context window of 131,072 tokens holds about 262 pages of text at 500 tokens a page.

How this page is made

Prices, context sizes and abilities are read from One API's public price feed and its model endpoints each time this page is built. The time to the first token, the output speed and the price of a call are measured by us: 3 calls for each model through a One API key on 22 November 2026, entering at not recorded. A model that did not answer has no page. How we measure.

Data checked · Last changed

Get an API key