LLM Pricing
← All models

meta.llama4-maverick-17b-instruct-v1:0

bedrock_converse · chat model

Input
$0.2400 / 1M tokens
Output
$0.9700 / 1M tokens
Cached input
N/A
Context
4.1K

Pricing

Item Raw value (per token) Normalized
Input 2.4e-7 $0.2400 / 1M tokens
Output 9.7e-7 $0.9700 / 1M tokens
Embedding 2.4e-7 $0.2400 / 1M tokens
Batch input 1.2e-7 $0.1200 / 1M tokens
Batch output 4.85e-7 $0.4850 / 1M tokens

Token limits

Context window
4.1K
Max input tokens
128.0K
Max output tokens
4.1K
Max tokens
4.1K

Capabilities

Capability Supported
Vision No
Function calling Yes
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
us.meta.llama4-maverick-17b-instruct-v1:0 bedrock_converse $0.2400 / 1M tokens $0.9700 / 1M tokens 4.1K N/A Tools
qwen3-omni-30b-a3b-thinking novita $0.2500 / 1M tokens $0.9700 / 1M tokens 16.4K N/A Vision Tools Reasoning
qwen3-omni-30b-a3b-instruct novita $0.2500 / 1M tokens $0.9700 / 1M tokens 16.4K N/A Vision Tools
qwen3-coder OpenRouter $0.2200 / 1M tokens $0.9500 / 1M tokens 262.1K N/A Tools
mercury-coder-small vercel_ai_gateway $0.2500 / 1M tokens $1.0000 / 1M tokens 16.4K N/A
qwen3-235b-a22b-instruct-2507-maas vertex_ai-qwen_models $0.2500 / 1M tokens $1.0000 / 1M tokens 16.4K 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": 2.4e-7,
  "input_cost_per_token_batches": 1.2e-7,
  "litellm_provider": "bedrock_converse",
  "max_input_tokens": 128000,
  "max_output_tokens": 4096,
  "max_tokens": 4096,
  "mode": "chat",
  "output_cost_per_token": 9.7e-7,
  "output_cost_per_token_batches": 4.85e-7,
  "supported_modalities": [
    "text",
    "image"
  ],
  "supported_output_modalities": [
    "text",
    "code"
  ],
  "supports_function_calling": true,
  "supports_tool_choice": false
}