LLM Comparison Table

Compare 54 large language models across pricing Cost per 1 million tokens for input and output. Input tokens are what you send; output tokens are what the model generates. , context window The maximum number of tokens (roughly ¾ of a word each) a model can process in a single request — including your prompt, conversation history, and the model's response. , speed Tokens generated per second. Higher means faster responses. Varies by provider load and prompt length. , and quality benchmarks Standardised tests like MMLU (knowledge), GPQA (reasoning), HumanEval (coding), and Chatbot Arena (human preference). . Click any column header to sort.

Last updated: 30 May 2026 · Prices from official API documentation

Head-to-Head Compare

Open source only

54 models

ModelModel	ProviderProvider	Input /1MIn $/1M	Output /1MOut $/1M	ContextCtx	SpeedSpeed	QualityQual.	ValueValue
Mistral NemoBEST VALUEOSS	Mistral	$0.02	$0.03	131K	0 t/s	72	26182
Llama 3.1 8B InstructOSS	Meta	$0.02	$0.05	131K	0 t/s	68	16000
Phi 4OSS	Microsoft	$0.07	$0.14	16K	0 t/s	74	6103
Nova Micro 1.0	Amazon	$0.04	$0.14	128K	0 t/s	68	5978
Command R7B (12-2024)OSS	Cohere	$0.04	$0.15	128K	0 t/s	65	5328
Reka Flash 3	Reka	$0.10	$0.20	66K	0 t/s	74	4229
Nova Lite 1.0	Amazon	$0.06	$0.24	300K	0 t/s	72	3692
Llama 4 ScoutOSS	Meta	$0.08	$0.30	10.0M	120 t/s	79	3224
Gemini 2.0 Flash Lite	Google	$0.07	$0.30	1.0M	450 t/s	75	3077
Llama 3.3 70B InstructOSS	Meta	$0.10	$0.32	131K	80 t/s	71	2679
GPT-5 Nano	OpenAI	$0.05	$0.40	400K	0 t/s	78	2496
Gemini 2.0 Flash	Google	$0.10	$0.40	1.0M	400 t/s	81	2492
GPT-4.1 Nano	OpenAI	$0.10	$0.40	1.0M	200 t/s	75	2308
Gemini 2.5 Flash Lite	Google	$0.10	$0.40	1.0M	0 t/s	74	2277
Llama 3.1 70B InstructOSS	Meta	$0.40	$0.40	131K	0 t/s	77	1925
Qwen2.5 72B InstructOSS	Alibaba	$0.36	$0.40	131K	65 t/s	71	1821
Llama 4 MaverickOSS	Meta	$0.15	$0.60	1.0M	95 t/s	76	1559
GPT-4o-mini	OpenAI	$0.15	$0.60	128K	150 t/s	74	1518
Command R (08-2024)OSS	Cohere	$0.15	$0.60	128K	0 t/s	73	1497
Mistral Small 3.1 24BOSS	Mistral	$0.35	$0.56	128K	150 t/s	72	1429
DeepSeek V3.2OSS	DeepSeek	$0.20	$0.77	164K	49 t/s	77	1227
DeepSeek V3OSS	DeepSeek	$0.23	$0.91	131K	0 t/s	76	1023
Qwen2.5 Coder 32B InstructOSS	Alibaba	$0.66	$1.00	128K	0 t/s	82	896
Sonar	Perplexity	$1.00	$1.00	127K	0 t/s	74	740
Qwen3 235B A22BOSS	Alibaba	$0.46	$1.82	131K	40 t/s	87	588
GPT-4.1 Mini	OpenAI	$0.40	$1.60	1.0M	160 t/s	75	577
R1 0528OSS	DeepSeek	$0.50	$2.15	164K	0 t/s	83	478
DeepSeek R1OSS	DeepSeek	$0.70	$2.50	164K	30 t/s	85	415
Gemini 2.5 Flash	Google	$0.30	$2.50	1.0M	350 t/s	78	400
Nova Pro 1.0	Amazon	$0.80	$3.20	300K	0 t/s	78	300
Qwen3 MaxOSS	Alibaba	$0.78	$3.90	262K	0 t/s	85	272
O4 Mini	OpenAI	$1.10	$4.40	200K	65 t/s	90	252
Claude 3.5 Haiku	Anthropic	$0.80	$4.00	200K	120 t/s	76	238
o3 Mini	OpenAI	$1.10	$4.40	200K	60 t/s	84	235
Claude Haiku 4.5	Anthropic	$1.00	$5.00	200K	0 t/s	76	190
Mistral LargeOSS	Mistral	$2.00	$6.00	128K	80 t/s	73	146
O3	OpenAI	$2.00	$8.00	200K	15 t/s	88	135
GPT-4.1	OpenAI	$2.00	$8.00	1.0M	110 t/s	77	118
GPT-5	OpenAI	$1.25	$10.00	400K	75 t/s	87	111
Gemini 2.5 Pro	Google	$1.25	$10.00	1.0M	90 t/s	83	106
Command AOSS	Cohere	$2.50	$10.00	256K	0 t/s	80	98
Command R+ (08-2024)OSS	Cohere	$2.50	$10.00	128K	0 t/s	79	97
GPT-5.2	OpenAI	$1.75	$14.00	400K	85 t/s	90	82
Claude Sonnet 4.6	Anthropic	$3.00	$15.00	1.0M	90 t/s	86	72
Claude Sonnet 4	Anthropic	$3.00	$15.00	1.0M	80 t/s	79	66
Claude Sonnet 4.5	Anthropic	$3.00	$15.00	1.0M	0 t/s	79	66
GPT-4o (2024-05-13)	OpenAI	$5.00	$15.00	128K	100 t/s	75	60
Claude Opus 4.5	Anthropic	$5.00	$25.00	200K	0 t/s	86	43
o1	OpenAI	$15.00	$60.00	200K	0 t/s	84	17
Claude Opus 4.6	Anthropic	$15.00	$75.00	1.0M	50 t/s	89	15
O3 Pro	OpenAI	$20.00	$80.00	200K	0 t/s	88	14
Claude Opus 4	Anthropic	$15.00	$75.00	200K	30 t/s	84	14
GPT-5 Pro	OpenAI	$15.00	$120.00	400K	0 t/s	90	10
GPT-5.2 Pro	OpenAI	$21.00	$168.00	400K	0 t/s	93	7

Prices per 1M tokens (USD)Speed in output tokens/secondQuality: composite benchmark score (0-100)Value: quality per unit cost