QOURA
ModelsEveryday

Llama 3.3 70B

by Meta

Meta's widely used 70B. Predictable output that many prompts were written for.

Input

$0.26 per 1M tokens

Output

$0.60 per 1M tokens

Specs

Id for API calls
llama-3.3-70b
Maker
Meta
Reads
Text
Context
131K tokens
Endpoint
/v1/chat/completions
Billing
Metered per token against the key
Served by
A third-party model supplier, through the gateway

Once you hold a credit

  1. 1

    Redeem it in the dashboard

    A local proof covers the whole face-value set, and the balance lands on a key generated in your browser.

  2. 2

    Call Llama 3.3 70B

    Any OpenAI client works with the base URL https://qoura.xyz/v1 and your key.

curl https://qoura.xyz/v1/chat/completions \
  -H "Authorization: Bearer qk-..." \
  -H "Content-Type: application/json" \
  -d '{"model": "llama-3.3-70b", "max_tokens": 400,
       "messages": [{"role": "user", "content": "Summarise this changelog"}]}'
Read the privacy limits

More models

Kimi K3

Moonshot AI · Deep reasoning

$12.00per 1M out

1M contextFrom one dollar

GLM 5.3

Z.ai · Deep reasoning

$5.76per 1M out

1M contextFrom one dollar

DeepSeek V4 Pro

DeepSeek · Deep reasoning

$0.99per 1M out

1M contextFrom one dollar

Qwen3.5 397B

Qwen · Deep reasoning

$4.20per 1M out

262K contextFrom one dollar