LLM Pricing
← All models

devstral-small

vercel_ai_gateway · chat model

Input
$0.0700 / 1M tokens
Output
$0.2800 / 1M tokens
Cached input
N/A
Context
128.0K

Pricing

Item Raw value (per token) Normalized
Input 7e-8 $0.0700 / 1M tokens
Output 2.8e-7 $0.2800 / 1M tokens
Embedding 7e-8 $0.0700 / 1M tokens

Token limits

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

Capabilities

Capability Supported
Vision No
Function calling Yes
Parallel function calling No
Tool choice Yes
Prompt caching No
Reasoning No
Response schema Yes
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
mistral-7b-instruct perplexity $0.0700 / 1M tokens $0.2800 / 1M tokens 4.1K N/A
mixtral-8x7b-instruct perplexity $0.0700 / 1M tokens $0.2800 / 1M tokens 4.1K N/A
pplx-7b-chat perplexity $0.0700 / 1M tokens $0.2800 / 1M tokens 8.2K N/A
sonar-small-chat perplexity $0.0700 / 1M tokens $0.2800 / 1M tokens 16.4K N/A
ernie-4.5-21B-a3b-thinking novita $0.0700 / 1M tokens $0.2800 / 1M tokens 65.5K N/A Reasoning
ernie-4.5-21B-a3b novita $0.0700 / 1M tokens $0.2800 / 1M tokens 8.0K 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": 7e-8,
  "litellm_provider": "vercel_ai_gateway",
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "max_tokens": 128000,
  "mode": "chat",
  "output_cost_per_token": 2.8e-7,
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true
}