Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. GPT-6.1 TerraOpenAIRemove
  2. Devstral 2 2512Mistral AIRemove
  3. Gemini 4 CarbonGoogleRemove
gpt-6.1-terra vs devstral-2512 vs gemini-4-carbon
AttributeGPT-6.1 Terragpt-6.1-terraDevstral 2 2512devstral-2512Gemini 4 Carbongemini-4-carbon
Pricing
Input$1.00 / 1M$0.15 / 1M$2.00 / 1M
Output$5.00 / 1M$0.60 / 1M$10.00 / 1M
Cache Write (5m)$1.00 / 1M$0.15 / 1M$2.00 / 1M
Cache Write (1h)$1.00 / 1M$0.15 / 1M$2.00 / 1M
Cache Read$1.00 / 1M$0.15 / 1M$2.00 / 1M
Web Search$0 / 1M$0 / 1M$0 / 1M
Context
Max context1M262.1K1M
Max outputN/AN/AN/A
Capabilities
VisionYesNoYes
Function CallingYesYesYes
JSON ModeYesYesYes
StreamingNoYesYes
Catalogue
ProviderOpenAIMistral AIGoogle
Categorychatchatchat
Charge typePay As You GoPay As You GoPay As You Go
Released———
Description
SummaryGPT-6.1 Terra is OpenAI’s mid-tier model in the GPT-6.1 series, designed to balance capability, speed, and cost efficiency. Positioned below GPT-6.1 Sol, it delivers strong performance across everyday agentic workflows, coding, and professional writing, with particular strengths in screenshot understanding and on-screen content analysis. Optimized for high-volume production workloads, GPT-6.1 Terra is well suited for coding assistants, visual interface analysis, workflow automation, and scalable agentic applications that require reliable performance at an accessible cost.Devstral 2 is Mistral AI's open-source, agentic coding model — a 123B dense transformer with a 256K context window. It can navigate and modify large codebases, coordinate multi-file changes, manage dependencies, and automatically detect and fix errors. Designed for modernization and large engineering tasks, it’s tunable for specific languages or enterprise code and is released under a modified MIT license.Gemini 4 Carbon is Google's frontier multimodal reasoning model, designed for advanced coding, agentic workflows, and complex multi-step problem solving. It supports text, image, audio, video, and file inputs, enabling integrated reasoning and analysis across diverse modalities. Optimized for long-horizon execution and demanding professional workloads, Gemini 4 Carbon supports up to 1M output tokens through continuation and configurable reasoning effort levels (low, medium, high) to balance reasoning depth, latency, and cost. It is well suited for autonomous agents, software engineering, multimodal analysis, and large-scale workflow automation.