Roundup
Best AI Models for Coding
Which frontier models actually hold up in multi-file refactors, agentic tooling and test-driven work, and what they cost per million tokens.
deepseek/deepseek-v3.1-terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
Source: OpenRouter (live)
Prices as listed on OpenRouter, refreshed every five minutes. Provider-direct prices may differ. Convert to your currency on the AI Tracker.
Price history
32 daily snapshots from 24 Sept 2026 to 3 Nov 2026. Blended = 75% input / 25% output. See all changes on Market Movers.
Capabilities
Capabilities are read from the provider listing. "Not declared" means the listing does not advertise the feature, not that it is absent.
Why it costs this
Alternatives
$0.525
/M blended
$0.075
/M blended
DeepSeek
$0.159
/M blended
$0.323
/M blended
DeepSeek: DeepSeek V4 Pro 0813
DeepSeek
$1.09
/M blended
DeepSeek: DeepSeek V4 Flash 0731
DeepSeek
$0.119
/M blended
Alternatives
OpenAI
$0.450
/M blended
OpenAI
$0.450
/M blended
Z.ai (Zhipu)
$0.450
/M blended
Mistral
$0.450
/M blended
MiniMax
$0.446
/M blended
OpenAI
$0.463
/M blended
Within ±50% of $0.453/M blended.
Analysis
Roundup
Which frontier models actually hold up in multi-file refactors, agentic tooling and test-driven work, and what they cost per million tokens.
Review
Open-weight, remarkably cheap and genuinely capable. Where DeepSeek fits and what to watch for.
Low-cost open-weight reasoning and chat models. All DeepSeek models · Official site
Newsletter
Get the most important developments in artificial intelligence delivered directly to your inbox.
No hype. No spam.
Just trusted insights, major model releases, pricing updates, benchmark changes, product reviews, and practical guidance from across the AI ecosystem.
The AI HQ Briefing
One email a week. Read in five minutes.