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.
Provider
Low-cost open-weight reasoning and chat models.
Catalogue
Newest listings first. Prices are USD per million tokens as listed on OpenRouter.
| Model | Input | Output | Blended | Context | Capabilities | Listed |
|---|---|---|---|---|---|---|
| DeepSeek: DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.150 | $0.600 | $0.262 | 1.0M | ToolsReasoningJSONImage | |
| DeepSeek: DeepSeek V4 Flash Vision Exp (batch) deepseek/deepseek-v4-flash-vision-exp:batch | $0.110 | $0.330 | $0.165 | 1.0M | ToolsReasoningJSONImage | |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.216 | $0.647 | $0.323 | 1.0M | ToolsReasoningJSONImage | |
| DeepSeek: DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.532 | $1.60 | $0.798 | 1.0M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V4 Pro 0813 (batch) deepseek/deepseek-v4-pro-0813:batch | $0.660 | $1.98 | $0.990 | 1.0M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.040 | $0.080 | $0.050 | 1.3M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V4 Flash 0731 (batch) deepseek/deepseek-v4-flash-0731:batch | $0.110 | $0.330 | $0.165 | 1.0M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V4 Pro 0423 deepseek/deepseek-v4-pro | $0.422 | $0.845 | $0.528 | 1.0M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash | $0.036 | $0.071 | $0.044 | 1.0M | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.269 | $0.400 | $0.302 | 164K | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3.2 Exp deepseek/deepseek-v3.2-exp | $0.270 | $0.410 | $0.305 | 164K | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus | $0.270 | $1.00 | $0.453 | 164K | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 | $0.250 | $0.950 | $0.425 | 164K | ToolsReasoningJSON | |
| DeepSeek: R1 0528 deepseek/deepseek-r1-0528 | $0.500 | $2.15 | $0.913 | 164K | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3 0324 deepseek/deepseek-chat-v3-0324 | $0.250 | $1.00 | $0.438 | 164K | ToolsJSON | |
| DeepSeek: R1 Distill Llama 70B deepseek/deepseek-r1-distill-llama-70b | $0.800 | $0.800 | $0.800 | 8K | Reasoning | |
| DeepSeek: R1 deepseek/deepseek-r1 | $0.700 | $2.50 | $1.15 | 64K | ToolsReasoningJSON | |
| DeepSeek: DeepSeek V3 deepseek/deepseek-chat | $0.320 | $0.890 | $0.462 | 164K | ToolsJSON |
Capability chips reflect what the listing declares; absence is not evidence a feature is missing.
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.
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.