LLM Pricing
← All models

databricks-meta-llama-3-1-8b-instruct

databricks · chat model

Input
$0.1500 / 1M tokens
Output
$0.4500 / 1M tokens
Cached input
N/A
Context
128.0K

Pricing

Item Raw value (per token) Normalized
Input 1.5000999999999998e-7 $0.1500 / 1M tokens
Output 4.5003000000000007e-7 $0.4500 / 1M tokens
Embedding 1.5000999999999998e-7 $0.1500 / 1M tokens

Token limits

Context window
128.0K
Max input tokens
200.0K
Max output tokens
128.0K
Max tokens
128.0K

Capabilities

Capability Supported
Vision No
Function calling No
Parallel function calling No
Tool choice No
Prompt caching No
Reasoning No
Response schema No
System messages No
Audio input No
Audio output No
Web search No
PDF input No
Video input No

Similar models

Models with comparable pricing in the same mode (chat).

Model Provider Input Output Context Coding Features
QwQ-32B nebius $0.1500 / 1M tokens $0.4500 / 1M tokens 32.8K N/A Tools Reasoning
gpt-4.1-nano-2025-04-14 Azure $0.1100 / 1M tokens $0.4400 / 1M tokens 32.8K N/A Vision Tools Cache
databricks-gemma-3-12b databricks $0.1500 / 1M tokens $0.5000 / 1M tokens 32.0K N/A
qwen3-32b-fp8 novita $0.1000 / 1M tokens $0.4500 / 1M tokens 20.0K N/A Reasoning
QwQ-32B deepinfra $0.1500 / 1M tokens $0.4000 / 1M tokens 131.1K N/A Tools
llama-3.3-70b-instruct novita $0.1350 / 1M tokens $0.4000 / 1M tokens 120.0K N/A Tools

Sources

Pricing source LiteLLM model cost map
Synced at 2026-05-27
Manual review Not reviewed
Raw LiteLLM fields
{
  "input_cost_per_token": 1.5000999999999998e-7,
  "input_dbu_cost_per_token": 0.0000021429999999999996,
  "litellm_provider": "databricks",
  "max_input_tokens": 200000,
  "max_output_tokens": 128000,
  "max_tokens": 128000,
  "metadata": {
    "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
  },
  "mode": "chat",
  "output_cost_per_token": 4.5003000000000007e-7,
  "output_dbu_cost_per_token": 0.000006429000000000001,
  "source": "https://www.databricks.com/product/pricing/foundation-model-serving"
}