DEFAULT PICK5d
DeepSeek · 1M context · released Apr 24
$/1M out
$0.280
$0.140 in
Q/$
B#34 of 98
quality per $
SWE-bench Pro
52.6%
SWE-bench Pro · 98 priced candidates
Best Q/$ at this budget. SWE-bench Pro 52.6 on DeepSeek Platform drives the rank.
checked today
1,713 models · 132 providers · 231 labs
Pick the right model in 30 seconds.
Benchmark-backed, price-aware, refreshed daily.
Shortlist · coding / ≤ $5 / 200K + tools
Three picks, ranked by quality per dollar
ALT PICK30d
DeepSeek · 160K context · released Jan 1
$/1M out
$0.378
$0.252 in
Q/$
B#35 of 98
quality per $
SWE-bench Verified
70%
SWE-bench Verified · 98 priced candidates
Alternate pick — competitive SWE-bench Verified at 70.0 with OpenRouter pricing.
BUDGET PICK30d
DeepSeek · 164K context · released Apr 10
$/1M out
$0.410
$0.270 in
Q/$
B#39 of 98
quality per $
SWE-bench Verified
68.4%
SWE-bench Verified · 98 priced candidates
Budget pick — same task fit, cheapest output on OpenRouter.
Pulse · this week
What changed in the model market
99new models
Composer 2.5 · Sora 2 · GPT-5.3
78price cuts
Verified provider price reductions
13benchmark refreshes
646 scores tracked across major suites
cheapest output · $/1M
$0CoBuddy
Cheat sheet
Most-asked comparisons
GPT-5.5vsClaude Opus 4.7GPT-5.5vsGemini 3.1 Pro PreviewClaude Opus 4.7vsDeepSeek V4 ProDeepSeek V4 ProvsGLM-5.1Kimi K2.6vsDeepSeek V4 ProClaude Sonnet 4.6vsDeepSeek V4 Flash
Browse everything — 1,713 models · 132 providers · 231 labs