gemini-2.5-flash vs devstral-small-2507

Pricing, Performance & Features Comparison

Price unit:

gemini-2.5-flash

Authorgoogle

Context Length1M

Reasoning

Providers1

ReleasedJun 2025

Knowledge CutoffJan 2025

License-

Gemini 2.5 Flash is our best model in terms of price and performance, and offers well-rounded capabilities.

Input$0.15

Output$0.6

Latency (p50)1.5s

Output Limit66K

Function Calling

JSON Mode

Input-

Output-

google-vertex

in$0.15out$0.6--

Latency (24h)

Success Rate (24h)

devstral-small-2507

Authormistral

Context Length128K

Reasoning

Providers1

ReleasedJul 2025

Knowledge Cutoff-

License-

Devstral-Small-2507 is an agentic Large Language Model (LLM) developed by Mistral AI and All Hands AI specifically for software engineering tasks. It excels at using tools to explore codebases, edit multiple files, and power software engineering agents. This model is notable for its remarkable performance on the SWE-bench benchmark, where it is positioned as the #1 open-source model.

Input$0.1

Output$0.3

Latency (p50)638ms

Output Limit128K

Function Calling

JSON Mode

InputText

OutputText

mistral

in$0.1out$0.3--