Model finder

Find a model

Describe the need; the atlas applies deterministic rules to observed attributes, current prices and current benchmark results and returns the models that satisfy them — sorted by how many criteria they meet, then best benchmark rank, then release date. No composite score, no single winner.

125 models satisfy at least one of the criteriaNo single winner — these are the observed dimensions; the order is criteria met → best rank → release date.

use case visiondeployment apimax output price 5

Model	Why	Observed dimensions	Deployments	Ranks
DeepSeek-V4.1-FlashOpen weightsDeepSeek	cheapest output $0.6/M ≤ $5 modalities include image	1M context · image · text · reasoning · tool calling · released 10 Sept 2026 · from $0.15 in / $0.60 out · 3 providers	OpenRouter$0.15 / $0.60 DeepSeek API$0.15 / $0.60 Fireworks AI$0.22 / $0.66 DeepSeek API$0.30 / $1.2	livebench-agentic-coding#1 livebench-2#5 livebench-data-analysis#12+9
Gemini 3.8 FlashProprietaryGoogle	cheapest output $1.875/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 2 Sept 2026 · from $0.375 in / $1.88 out · 2 providers	Google Gemini API$0.375 / $1.88 OpenRouter$0.375 / $1.88 OpenRouter$0.75 / $3.75 Google Gemini API$0.75 / $3.75 +1 more	livebench-if#1 gpqa-diamond#2 mmmu-pro#2+10
gpt-5.6-solProprietaryOpenAI	cheapest output $5/M ≤ $5 modalities include image	1.05M context · image · text · reasoning · tool calling · released 9 Jul 2026 · from $1 in / $5 out · 2 providers	OpenRouter$1 / $5 OpenAI API$1 / $5 OpenAI API$2 / $10 OpenRouter$2 / $10 +1 more	terminal-bench#1 livebench-coding#3 livebench-mathematics#3+13
Grok 4.3ProprietaryxAI	cheapest output $2/M ≤ $5 modalities include image	1M context · document · image · text · reasoning · tool calling · released 30 Apr 2026 · from $1 in / $2 out · 2 providers	OpenRouter$1 / $2 xAI API$1 / $2 xAI API$1.25 / $2.5 xAI API$1.25 / $2.5 +1 more	ifbench#1 tau2-bench#9 mmmu-pro#30+13
gpt-5ProprietaryOpenAI	cheapest output $5/M ≤ $5 modalities include image	400K context · document · image · text · reasoning · tool calling · released 7 Aug 2025 · from $0.625 in / $5 out · 2 providers	OpenRouter$0.625 / $5 OpenAI API$0.625 / $5 OpenAI API$1.25 / $10 OpenRouter$1.25 / $10 +1 more	aider-polyglot#1 swe-bench-verified#17 ifbench#42+7
o3ProprietaryOpenAI	cheapest output $4/M ≤ $5 modalities include image	200K context · document · image · text · reasoning · tool calling · released 16 Apr 2025 · from $1 in / $4 out · 2 providers	OpenAI API$1 / $4 OpenRouter$1 / $4 OpenAI API$2 / $8 OpenRouter$2 / $8 +1 more	swe-bench-multimodal#1 aider-polyglot#4 swe-bench-verified#22+8
Gemma 3 27BOpen weightsGoogle	cheapest output $0.45/M ≤ $5 modalities include image	131.1K context · image · text · tool calling · released 12 Mar 2025 · from $0.08 in / $0.45 out · 2 providers	OpenRouter$0.08 / $0.45 Google Gemini API$0.08 / $0.45	aider-polyglot-well-formed#1 aider-polyglot#60 scicode#123+7
GPT-4o-mini (2024-07-18)OpenAI	cheapest output $0.6/M ≤ $5 modalities include image	128K context · document · image · text · tool calling · released 18 Jul 2024 · from $0.15 in / $0.60 out · 2 providers	OpenRouter$0.15 / $0.60 OpenAI API$0.15 / $0.60	aider-polyglot-well-formed#1 aider-polyglot#61
Gemini 3.7 FlashProprietaryGoogle	cheapest output $1.875/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 13 Aug 2026 · from $0.375 in / $1.88 out · 2 providers	Google Gemini API$0.375 / $1.88 OpenRouter$0.375 / $1.88 Google Gemini API$0.75 / $3.75 OpenRouter$0.75 / $3.75 +1 more	livebench-if#2 mmmu-pro#3 scicode#3+10
o4-miniProprietaryOpenAI	cheapest output $2.2/M ≤ $5 modalities include image	200K context · document · image · text · reasoning · tool calling · released 16 Apr 2025 · from $0.55 in / $2.2 out · 2 providers	OpenRouter$0.55 / $2.2 OpenAI API$0.55 / $2.2 OpenAI API$1.1 / $4.4 OpenRouter$1.1 / $4.4 +1 more	swe-bench-multimodal#2 aider-polyglot#10 swe-bench-verified#31+8
MiniMax-M3Open weightsMiniMax	cheapest output $1.2/M ≤ $5 modalities include image	427B params · 1.05M context · Other · image · text · video · reasoning · tool calling · released 2 Jun 2026 · from $0.30 in / $1.2 out · 4 providers	OpenRouter$0.30 / $1.2 OpenRouter$0.30 / $1.2 Together AI$0.30 / $1.2 MiniMax API$0.30 / $1.2 +1 more	ifbench#3 gpqa-diamond#14 mmmu-pro#26+13
gpt-4.1ProprietaryOpenAI	cheapest output $4/M ≤ $5 modalities include image	1.05M context · document · image · text · tool calling · released 14 Apr 2025 · from $1 in / $4 out · 2 providers	OpenAI API$1 / $4 OpenRouter$1 / $4 OpenRouter$2 / $8 OpenAI API$2 / $8 +1 more	swe-bench-multimodal#3 aider-polyglot-well-formed#20 aider-polyglot#28+8
Muse Spark 1.3ProprietaryMeta AI	cheapest output $4.25/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 2 Sept 2026 · from $1.25 in / $4.25 out · 1 provider	OpenRouter$1.25 / $4.25	livebench-2#4 livebench-if#4 scicode#4+10
DeepSeek V4 Flash Vision ExpOpen weightsDeepSeek	cheapest output $0.33/M ≤ $5 modalities include image	304.6B params · 1.05M context · MIT · image · text · reasoning · tool calling · released 31 Aug 2026 · from $0.11 in / $0.33 out · 3 providers	OpenRouter$0.11 / $0.33 DeepSeek API$0.11 / $0.33 DeepSeek API$0.22 / $0.66 Fireworks AI$0.22 / $0.66 +1 more	livebench-agentic-coding#4 livebench-data-analysis#8 livebench-2#21+5
Step 3.7 FlashOpen weightsStepFun	cheapest output $1.15/M ≤ $5 modalities include image	262.1K context · image · text · video · reasoning · tool calling · released 28 May 2026 · from $0.20 in / $1.15 out · 1 provider	OpenRouter$0.20 / $1.15	tau2-bench#4 mmmu-pro#44 terminal-bench#54+5
GLM 5V TurboProprietaryZ.ai (Zhipu AI)	cheapest output $4/M ≤ $5 modalities include image	202.8K context · image · text · video · reasoning · tool calling · released 1 Apr 2026 · from $1.2 in / $4 out · 2 providers	OpenRouter$1.2 / $4 Z.ai API$1.2 / $4	tau2-bench#4 mmmu-pro#65 terminal-bench#74+4
gpt-4oProprietaryOpenAI	cheapest output $5/M ≤ $5 modalities include image	128K context · document · image · text · tool calling · released 13 May 2024 · from $1.25 in / $5 out · 2 providers	OpenAI API$1.25 / $5 OpenRouter$1.25 / $5 OpenRouter$2.5 / $10 OpenAI API$2.5 / $10 +1 more	swe-bench-multimodal#4 swe-bench-verified#38 terminal-bench#176+5
Qwen3.8 FlashOpen weightsQwen	cheapest output $0.47/M ≤ $5 modalities include image	1M context · image · text · video · reasoning · tool calling · released 26 Aug 2026 · from $0.15 in / $0.47 out · 2 providers	OpenRouter$0.15 / $0.47 Together AI$0.15 / $0.47	livebench-if#5 livebench-agentic-coding#10 artificial-analysis-intelligence-index#17+10
gpt-5.6-lunaProprietaryOpenAI	cheapest output $0.6/M ≤ $5 modalities include image	1.05M context · image · text · reasoning · tool calling · released 9 Jul 2026 · from $0.10 in / $0.60 out · 2 providers	OpenAI API$0.10 / $0.60 OpenRouter$0.10 / $0.60 OpenAI API$0.20 / $1.2 OpenAI API$0.20 / $1.2 +1 more	livebench-coding#5 livebench-data-analysis#22 scicode#22+10
Gemini 3.5 FlashProprietaryGoogle	cheapest output $4.5/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 19 May 2026 · from $0.75 in / $4.5 out · 2 providers	OpenRouter$0.75 / $4.5 Google Gemini API$0.75 / $4.5 Google Gemini API$1.5 / $9 Google Gemini API$1.5 / $9 +1 more	mmmu-pro#5 livebench-if#7 livebench-language#11+13
Grok 4.20ProprietaryxAI	cheapest output $2.5/M ≤ $5 modalities include image	1M context · document · image · text · reasoning · tool calling · released 31 Mar 2026 · from $1.25 in / $2.5 out · 2 providers	xAI API$1.25 / $2.5 OpenRouter$1.25 / $2.5 xAI API$1.25 / $2.5	ifbench#5 gpqa-diamond#31 tau2-bench#41+4
Gemini 3.6 FlashProprietaryGoogle	cheapest output $1.875/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 21 Jul 2026 · from $0.375 in / $1.88 out · 2 providers	OpenRouter$0.375 / $1.88 Google Gemini API$0.375 / $1.88 Google Gemini API$0.75 / $3.75 Google Gemini API$0.75 / $3.75 +1 more	mmmu-pro#7 livebench-if#9 livebench-language#13+10
Muse Spark 1.1ProprietaryMeta AI	cheapest output $4.25/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 16 Jul 2026 · from $1.25 in / $4.25 out · 1 provider	OpenRouter$1.25 / $4.25	scicode#7 humanitys-last-exam#12 livebench-agentic-coding#16+9
Kimi K2.5Open weightsMoonshot AI	cheapest output $2.25/M ≤ $5 modalities include image	1.03T params · 262.1K context · Other · image · text · reasoning · tool calling · released 1 Jan 2026 · from $0.45 in / $2.25 out · 2 providers	OpenRouter$0.45 / $2.25 Moonshot AI Platform$0.45 / $2.25	swe-bench-multilingual#7 swe-bench-verified#10 tau2-bench#14+6
Muse Spark 1.2ProprietaryMeta AI	cheapest output $4.25/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 5 Aug 2026 · from $1.25 in / $4.25 out · 1 provider	OpenRouter$1.25 / $4.25	livebench-reasoning#9 livebench-if#10 scicode#10+9
Qwen3.6 PlusProprietaryQwen	cheapest output $1.95/M ≤ $5 modalities include image	1M context · image · text · video · reasoning · tool calling · released 2 Apr 2026 · from $0.325 in / $1.95 out · 2 providers	OpenRouter$0.325 / $1.95 Together AI$0.50 / $3	tau2-bench#9 livebench-coding#24 terminal-bench#24+12
Qwen3.8 27BOpen weightsQwen	cheapest output $2.55/M ≤ $5 modalities include image	27.8B params · 1M context · Apache-2.0 · image · text · video · reasoning · tool calling · released 5 Aug 2026 · from $0.214 in / $2.55 out · 2 providers	OpenRouter$0.214 / $2.55 GroqCloud$0.80 / $4	livebench-agentic-coding#11 livebench-if#16 livebench-data-analysis#24+10
gpt-5.4-miniProprietaryOpenAI	cheapest output $2.25/M ≤ $5 modalities include image	400K context · document · image · text · reasoning · tool calling · released 17 Mar 2026 · from $0.375 in / $2.25 out · 2 providers	OpenRouter$0.375 / $2.25 OpenAI API$0.375 / $2.25 OpenAI API$0.75 / $4.5 OpenRouter$0.75 / $4.5 +1 more	terminal-bench#11 scicode#26 ifbench#40+13
Qwen3.5 397B A17BOpen weightsQwen	cheapest output $3.5/M ≤ $5 modalities include image	262.1K context · image · text · video · reasoning · tool calling · released 16 Feb 2026 · from $0.55 in / $3.5 out · 2 providers	OpenRouter$0.55 / $3.5 Together AI$0.60 / $3.6	ifbench#11 tau2-bench#18 mmmu-pro#32+5
GLM 5.3 FlashOpen weightsZ.ai (Zhipu AI)	cheapest output $0.25/M ≤ $5 modalities include image	321.3B params · 1.31M context · MIT · image · text · video · reasoning · tool calling · released 25 Aug 2026 · from $0.075 in / $0.25 out · 4 providers	Z.ai API$0.075 / $0.25 OpenRouter$0.075 / $0.25 OpenRouter$0.15 / $0.50 Z.ai API$0.15 / $0.50 +1 more	artificial-analysis-intelligence-index#12 livebench-coding#19 livebench-agentic-coding#21+9
Qwen 3.7 PlusProprietaryQwen	cheapest output $1.28/M ≤ $5 modalities include image	1M context · image · text · reasoning · tool calling · released 3 Jun 2026 · from $0.32 in / $1.28 out · 3 providers	OpenRouter$0.32 / $1.28 Together AI$0.32 / $1.28 Fireworks AI$0.40 / $1.6	ifbench#12 mmmu-pro#15 terminal-bench#16+5
Gemini 3 Flash PreviewProprietaryGoogle	cheapest output $1.5/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 17 Dec 2025 · from $0.25 in / $1.5 out · 2 providers	OpenRouter$0.25 / $1.5 Google Gemini API$0.25 / $1.5 Google Gemini API$0.50 / $3 Google Gemini API$0.50 / $3 +1 more	ifbench#12 mmmu-pro#18 terminal-bench#40+4
Claude Sonnet 5ProprietaryAnthropic	cheapest output $5/M ≤ $5 modalities include image	1M context · image · text · reasoning · tool calling · released 30 Jun 2026 · from $1 in / $5 out · 2 providers	Anthropic API$1 / $5 OpenRouter$1 / $5 OpenRouter$2 / $10 Anthropic API$2 / $10 +1 more	livebench-coding#13 livebench-agentic-coding#15 livebench-mathematics#15+10
gpt-5-miniProprietaryOpenAI	cheapest output $1/M ≤ $5 modalities include image	400K context · document · image · text · reasoning · tool calling · released 7 Aug 2025 · from $0.125 in / $1 out · 2 providers	OpenRouter$0.125 / $1 OpenAI API$0.125 / $1 OpenRouter$0.25 / $2 OpenAI API$0.25 / $2 +1 more	swe-bench-multilingual#13 swe-bench-verified#24 ifbench#30+7
Kimi K2.6Open weightsMoonshot AI	cheapest output $4/M ≤ $5 modalities include image	1.03T params · 262.1K context · Other · image · text · reasoning · tool calling · released 14 Apr 2026 · from $0.95 in / $4 out · 3 providers	Moonshot AI Platform$0.95 / $4 OpenRouter$0.95 / $4 Fireworks AI$0.95 / $4	tau2-bench#14 mmmu-pro#21 ifbench#22+13
gpt-5.1ProprietaryOpenAI	cheapest output $5/M ≤ $5 modalities include image	400K context · document · image · text · reasoning · tool calling · released 13 Nov 2025 · from $0.625 in / $5 out · 2 providers	OpenAI API$0.625 / $5 OpenRouter$0.625 / $5 OpenRouter$1.25 / $10 OpenAI API$1.25 / $10 +1 more	swe-bench-verified#15 terminal-bench#21 mmmu-pro#39+5
Gemini 3.1 Flash-Lite PreviewProprietaryGoogle	cheapest output $1.5/M ≤ $5 modalities include image	1.05M context · audio · document · image · text · video · reasoning · tool calling · released 3 Mar 2026 · from $0.25 in / $1.5 out · 2 providers	OpenRouter$0.25 / $1.5 Google Gemini API$0.25 / $1.5	ifbench#16 mmmu-pro#38 scicode#66+5
Llama 4 MaverickOpen weightsMeta AI	cheapest output $0.696/M ≤ $5 modalities include image	1.05M context · image · text · tool calling · released 5 Apr 2025 · from $0.20 in / $0.696 out · 1 provider	OpenRouter$0.20 / $0.696	aider-polyglot-well-formed#17 aider-polyglot#54 mmmu-pro#101+7
Qwen3.6 35B A3BOpen weightsQwen	cheapest output $0.9/M ≤ $5 modalities include image	36B params · 262.1K context · Apache-2.0 · image · text · video · reasoning · tool calling · released 15 Apr 2026 · from $0.10 in / $0.90 out · 1 provider	OpenRouter$0.10 / $0.90	tau2-bench#22 mmmu-pro#45 terminal-bench#59+5
gpt-5.4-nanoProprietaryOpenAI	cheapest output $0.625/M ≤ $5 modalities include image	400K context · document · image · text · reasoning · tool calling · released 17 Mar 2026 · from $0.10 in / $0.625 out · 2 providers	OpenRouter$0.10 / $0.625 OpenAI API$0.10 / $0.625 OpenAI API$0.20 / $1.25 OpenAI API$0.20 / $1.25 +1 more	livebench-mathematics#22 ifbench#23 terminal-bench#30+13

Green chips = criteria satisfied by an observed fact; dashed amber = satisfied by an estimate (hardware fit). Ranks are positions inside each benchmark's primary comparability group.

MethodDeterministic filters over observed attributes, current prices and current benchmark results of canonical models; sorted by number of satisfied criteria, then best benchmark rank, then release date. No composite score. Hardware fit is an estimate. /methodology