Skip to main content
Glama

gpt-4o-mini-2024-07-18 vs devstral-medium-2507

Pricing, Performance & Features Comparison

Price unit:
Authoropenai
Context Length128K
Reasoning
-
Providers1
ReleasedJul 2024
Knowledge CutoffOct 2023
License-

GPT-4o-mini is a cost-effective and high-performing large language model from OpenAI, capable of handling both text and image inputs. It supports advanced features such as JSON Mode and parallel function calling, and can handle up to 128,000 tokens in its context window. This makes it an excellent choice for a variety of AI tasks, including those requiring large-scale context processing.

Input$0.15
Output$0.6
Latency (p50)1.1s
Output Limit16K
Function Calling
JSON Mode
InputText, Image
OutputText
in$0.15out$0.6cache$0.075-
Latency (24h)
Success Rate (24h)
Authormistral
Context Length128K
Reasoning
-
Providers1
ReleasedJul 2024
Knowledge Cutoff-
License-

Devstral Medium 2507 is a high-performance, code-centric large language model designed for agentic coding capabilities and enterprise use. It features a 128k token context window and achieves a 61.6% score on SWE-Bench Verified, outperforming several commercial models like Gemini 2.5 Pro and GPT-4.1. The model excels at code generation, multi-file editing, and powering software engineering agents with structured outputs and tool integration.

Input$0.4
Output$2
Latency (p50)773ms
Output Limit128K
Function Calling
JSON Mode
InputText
OutputText
in$0.4out$2--
Latency (24h)
Success Rate (24h)