Artificial Analysis LLM Performance Leaderboard

Independent performance benchmarks & pricing across API providers of LLMs. Definitions are below the table.
For further analysis and methodology, see artificialanalysis.ai.

	Features	Model Intelligence	Price	Output tokens/s	Latency
						Further Analysis
o3-mini (high)	200k	66	$1.93	202.9	36.43
o3-mini (high)	200k	66	$1.93	129.0	53.32
o3-mini	200k	63	$1.93	186.9	14.01
o3-mini	200k	63	$1.93	125.4	21.73
o1	200k	62	$26.25	99.8	28.36
o1	200k	62	$26.25	111.2	26.09
DeepSeek R1	64k	60	$0.96	25.8	4.23
DeepSeek R1	128k	60	$2.00	109.9	1.40
DeepSeek R1	128k	60	$2.36	65.9	0.44
DeepSeek R1 Base	128k	60	$1.20	24.0	0.66
DeepSeek R1 Fast	128k	60	$3.00	54.0	0.68
DeepSeek R1	128k	60	$3.99	69.3	0.57
DeepSeek R1	128k	60	$2.36	62.9	0.57
DeepSeek R1 (Fast)	164k	60	$4.25	108.3	0.83
DeepSeek R1 (Turbo, FP4)	33k	60	$1.50	88.7	0.29
DeepSeek R1	64k	60	$0.96	13.6	0.47
DeepSeek R1	128k	60	$4.00	58.8	0.45
DeepSeek R1 Turbo	64k	60	$1.15	32.8	0.78
DeepSeek R1	64k	60	$4.00	32.4	0.81
DeepSeek R1	16k	60	$5.50	256.4	2.22
DeepSeek R1	128k	60	$4.00	123.8	0.49
DeepSeek R1	128k	60	$7.00	25.2	0.68
QwQ-32B	131k	58	$0.20	120.5	1.23
QwQ-32B Base	131k	58	$0.23	44.3	0.64
QwQ-32B	131k	58	$0.65	82.2	0.51
QwQ-32B	131k	58	$0.90	131.1	0.63
QwQ-32B	131k	58	$0.14	39.0	0.34
QwQ-32B	33k	58	$0.18	22.4	1.17
QwQ-32B	131k	58	$0.32	398.6	0.12
QwQ-32B	16k	58	$0.63	352.4	0.93
QwQ-32B	131k	58	$1.20	89.2	0.53
Claude 3.7 Sonnet Thinking	200k	57	$6.00	57.4	0.00
Claude 3.7 Sonnet Thinking	200k	57	$6.00	78.5	0.97
o1-mini	128k	54	$1.93	225.3	10.34
o1-mini	128k	54	$2.12	194.5	14.47
DeepSeek R1 Distill Qwen 32B	128k	52	$0.14	49.4	0.24
DeepSeek R1 Distill Qwen 32B	64k	52	$0.30	20.9	1.12
DeepSeek R1 Distill Qwen 32B	128k	52	$0.69	138.1	0.38
DeepSeek V3 (Mar' 25)	64k	52	$0.48	32.9	4.07
DeepSeek V3 (Mar' 25)	128k	52	$1.45	43.9	1.21
DeepSeek V3 (Mar' 25)	128k	52	$1.25	36.1	0.82
DeepSeek V3 (Mar' 25)	128k	52	$0.75	29.9	0.66
DeepSeek V3 (Mar' 25)	164k	52	$0.80	76.3	0.57
DeepSeek V3 (Mar' 25)	160k	52	$0.90	63.6	0.84
DeepSeek V3 (Mar' 25)	164k	52	$0.52	21.4	0.39
DeepSeek V3 (Mar' 25)	64k	52	$1.20	31.7	0.65
DeepSeek V3 (Mar' 25)	8k	52	$1.13	267.5	2.21
DeepSeek V3 (Mar' 25)	128k	52	$1.25	27.1	0.70
Gemini 2.0 Pro Experimental (AI Studio)	2m	49	$0.00
DeepSeek R1 Distill Qwen 14B	64k	49	$0.15	45.2	0.71
DeepSeek R1 Distill Qwen 14B	128k	49	$1.60	150.0	0.26
DeepSeek R1 Distill Llama 70B	128k	48	$0.30	67.3	0.50
DeepSeek R1 Distill Llama 70B	66k	48	$0.94	1,928.1	0.18
DeepSeek R1 Distill Llama 70B Base	128k	48	$0.38	42.4	0.63
DeepSeek R1 Distill Llama 70B	128k	48	$0.34	33.0	0.42
DeepSeek R1 Distill Llama 70B	32k	48	$0.39	21.5	1.15
DeepSeek R1 Distill Llama 70B	128k	48	$0.81	275.2	0.22
DeepSeek R1 Distill Llama 70B (Spec decoding)	128k	48	$0.81	1,365.6	0.41
DeepSeek R1 Distill Llama 70B	16k	48	$0.88	124.0	0.98
DeepSeek R1 Distill Llama 70B	128k	48	$2.00	113.0	0.33
Claude 3.7 Sonnet	200k	48	$6.00	40.0	0.85
Claude 3.7 Sonnet	200k	48	$6.00	78.5	0.96
Gemini 2.0 Flash Vertex	1m	48	$0.26	247.4	0.31
Gemini 2.0 Flash (AI Studio)	1m	48	$0.17	258.4	0.34
Reka Flash 3	128k	47	$0.35	56.7	0.95
DeepSeek V3	66k	46	$0.48	29.8	4.02
DeepSeek V3 (FP8)	128k	46	$0.25	28.0	1.13
DeepSeek V3	128k	46	$0.75	18.1	0.70
DeepSeek V3	128k	46	$2.00	84.2	0.59
DeepSeek V3	128k	46	$1.31	64.3	0.86
DeepSeek V3	64k	46	$0.59	15.2	0.59
DeepSeek V3 Turbo	64k	46	$0.63	28.8	0.86
DeepSeek V3	64k	46	$0.89	29.0	0.97
DeepSeek V3 (FP8)	128k	46	$1.25	39.1	0.73
Qwen2.5 Max	32k	45	$2.80	35.8	1.13
Gemini 1.5 Pro (Sep) (Vertex)	2m	45	$2.19	94.4	0.51
Gemini 1.5 Pro (Sep) (AI Studio)	2m	45	$2.19	95.6	0.47
Claude 3.5 Sonnet (Oct)	200k	44	$6.00	47.5	0.93
Claude 3.5 Sonnet (Oct) Vertex	200k	44	$6.00	79.4	0.92
Claude 3.5 Sonnet (Oct)	200k	44	$6.00	79.0	1.40
Sonar	127k	43	$1.00	71.5	2.25
Sonar Pro	200k	43	$6.00	80.7	3.21
QwQ 32B-Preview	33k	43	$0.20	58.9	0.85
QwQ 32B-Preview	33k	43	$0.14	60.4	0.63
QwQ 32B-Preview	33k	43	$0.90	53.1	0.52
QwQ 32B-Preview	33k	43	$0.26	50.1	0.27
QwQ 32B-Preview	16k	43	$1.88	387.1	0.78
QwQ 32B-Preview	33k	43	$1.20	89.9	0.46
GPT-4o (Nov '24)	128k	41	$4.38	138.5	0.51
GPT-4o (Nov '24)	128k	41	$4.38	115.8	0.96
Gemini 2.0 Flash-Lite (Feb '25) (AI Studio)	1m	41	$0.13	206.2	0.26
Llama 3.3 70B (FP8)	128k	41	$0.17	34.7	0.57
Llama 3.3 70B	33k	41	$0.94	2,597.0	0.16
Llama 3.3 70B	128k	41	$0.40	40.4	1.56
Llama 3.3 70B	128k	41	$0.71	139.0	0.58
Llama 3.3 70B Fast	128k	41	$0.38	135.2	0.55
Llama 3.3 70B Base	128k	41	$0.20	17.5	0.76
Llama 3.3 70B	128k	41	$0.50	135.1	0.51
Llama 3.3 70B	128k	41	$0.71	47.9	0.45
Llama 3.3 70B	128k	41	$0.90	146.6	0.50
Llama 3.3 70B (Turbo, FP8)	128k	41	$0.20	40.0	0.38
Llama 3.3 70B	128k	41	$0.27	23.7	0.57
Llama 3.3 70B	128k	41	$0.60	157.8	0.36
Llama 3.3 70B	128k	41	$0.39	29.8	0.88
Llama 3.3 70B (Spec decoding)	8k	41	$0.69	1,554.8	0.41
Llama 3.3 70B	128k	41	$0.64	275.6	0.38
Llama 3.3 70B	128k	41	$0.75	450.5	0.33
Llama 3.3 70B Turbo	128k	41	$0.88	166.1	0.45
Llama 3.3 70B	128k	41	$0.70	9.7	1.08
GPT-4o (May '24)	128k	41	$7.50	137.0	0.40
GPT-4o (May '24)	128k	41	$7.50	69.7	1.09
Llama 3.1 405B (FP8)	128k	40	$0.80	34.8	0.65
Llama 3.1 405B	128k	40	$9.50	19.1	0.97
Llama 3.1 405B	128k	40	$4.00	12.9	0.79
Llama 3.1 405B Standard	128k	40	$2.40	30.7	1.84
Llama 3.1 405B Latency Optimized	128k	40	$3.00	64.6	0.73
Llama 3.1 405B Base	128k	40	$1.50	32.8	0.72
Llama 3.1 405B Vertex	128k	40	$7.75	29.7	0.39
Llama 3.1 405B	128k	40	$8.00	31.0	0.49
Llama 3.1 405B	128k	40	$3.00	84.6	0.64
Llama 3.1 405B	33k	40	$0.90	24.7	0.48
Llama 3.1 405B	16k	40	$6.25	170.3	1.24
Llama 3.1 405B	128k	40	$7.50	37.6	0.72
Llama 3.1 405B Turbo	128k	40	$3.50	114.9	0.68
Llama 3.1 405B	128k	40	$3.50	14.0	1.05
Qwen2.5 72B	131k	40	$0.40	20.6	1.57
Qwen2.5 72B	131k	40	$0.20	30.2	0.73
Qwen2.5 72B Fast	131k	40	$0.38	66.7	0.58
Qwen2.5 72B	131k	40	$0.90	41.1	0.43
Qwen2.5 72B	33k	40	$0.27	39.3	0.52
Qwen2.5 72B	16k	40	$0.94	243.9	0.84
Qwen2.5 72B Turbo	131k	40	$1.20	87.5	0.53
Qwen2.5 72B	131k	40	$0.00	61.3	1.08
MiniMax-Text-01	1m	40	$0.42	34.1	0.93
Phi-4	16k	40	$0.15	118.0	0.53
Phi-4	16k	40	$0.22	37.6	0.47
Phi-4	16k	40	$0.09	39.8	0.61
Command A	256k	40	$4.38	176.1	0.24
Tulu3 405B	16k	40	$6.25	184.6	1.27
Mistral Large 2 (Nov '24)	128k	38	$3.00	30.3	0.52
Mistral Large 2 (Nov '24)	128k	38	$3.00	35.0	0.53
Gemma 3 27B (AI_Studio)	128k	38	$0.00	59.4	0.72
Gemma 3 27B	128k	38	$0.07	45.9	0.48
Grok Beta	128k	38	$7.50	61.3	0.30
Pixtral Large	128k	37	$3.00	27.0	0.45
Qwen2.5 Instruct 32B Fast	128k	37	$0.20	82.5	0.54
Qwen2.5 Instruct 32B Base	128k	37	$0.10	59.7	0.57
Qwen2.5 Instruct 32B	128k	37	$0.79	198.2	0.23
Llama 3.1 Nemotron 70B (FP8)	128k	37	$0.17	35.5	0.62
Llama 3.1 Nemotron 70B Base	128k	37	$0.20	40.0	0.65
Llama 3.1 Nemotron 70B Fast	128k	37	$0.38	73.0	0.55
Llama 3.1 Nemotron 70B	128k	37	$0.27	29.8	0.60
Nova Pro	300k	37	$1.40	99.2	0.36
Nova Pro Latency Optimized	300k	37	$1.75	126.8	0.64
Mistral Large 2 (Jul '24)	128k	37	$3.00	37.2	0.50
Mistral Large 2 (Jul '24)	128k	37	$3.00	33.0	0.45
Mistral Large 2 (Jul '24)	128k	37	$3.00	35.6	0.51
Qwen2.5 Coder 32B	33k	36	$0.09	63.1	0.54
Qwen2.5 Coder 32B	131k	36	$0.20	58.1	0.74
Qwen2.5 Coder 32B	33k	36	$0.90	58.1	0.39
Qwen2.5 Coder 32B	33k	36	$0.10	48.4	0.58
Qwen2.5 Coder 32B	131k	36	$0.79	197.8	0.37
Qwen2.5 Coder 32B	16k	36	$0.63	339.9	0.74
Qwen2.5 Coder 32B	131k	36	$0.80	73.6	0.45
GPT-4o mini	128k	36	$0.26	71.2	0.36
GPT-4o mini	128k	36	$0.26	144.4	0.99
Llama 3.1 70B (FP8)	128k	35	$0.17	36.2	0.57
Llama 3.1 70B	128k	35	$0.40	56.7	1.12
Llama 3.1 70B Standard	128k	35	$0.72	31.5	0.66
Llama 3.1 70B Latency Optimized	128k	35	$0.90	140.0	0.34
Llama 3.1 70B Base	128k	35	$0.20	23.0	0.69
Llama 3.1 70B Fast	128k	35	$0.38	91.9	0.57
Llama 3.1 70B Vertex	128k	35	$0.00	73.0	0.26
Llama 3.1 70B	128k	35	$2.90	58.2	0.44
Llama 3.1 70B	128k	35	$0.90	148.4	0.45
Llama 3.1 70B (Turbo, FP8)	128k	35	$0.20	29.2	0.45
Llama 3.1 70B	128k	35	$0.27	36.2	0.34
Llama 3.1 70B	128k	35	$0.60	194.7	0.34
Llama 3.1 70B	32k	35	$0.35	42.2	1.14
Llama 3.1 70B	128k	35	$0.75	450.4	0.30
Llama 3.1 70B	128k	35	$1.50	54.1	0.50
Llama 3.1 70B Turbo	128k	35	$0.88	188.0	0.44
Llama 3.1 70B	128k	35	$0.90	125.6	0.51
Mistral Small 3.1	128k	35	$0.15	144.8	0.33
Mistral Small 3.1 Vertex	128k	35	$0.15	207.6	0.18
Mistral Small 3	32k	35	$0.15	149.6	0.33
Mistral Small 3	32k	35	$0.90	39.7	0.55
Mistral Small 3	32k	35	$0.09	70.0	0.26
Mistral Small 3	32k	35	$0.80	95.2	0.22
Claude 3 Opus	200k	35	$30.00	22.4	1.27
Claude 3 Opus Vertex	200k	35	$30.00	27.2	1.13
Claude 3 Opus	200k	35	$30.00	28.0	1.27
Claude 3.5 Haiku Standard	200k	35	$1.60	42.8	1.22
Claude 3.5 Haiku Latency Optimized	200k	35	$2.00	94.0	0.52
Claude 3.5 Haiku Vertex	200k	35	$1.60	65.4	0.62
Claude 3.5 Haiku	200k	35	$1.60	65.5	1.60
DeepSeek R1 Distill Llama 8B	32k	34	$0.04	45.2	0.63
Gemini 1.5 Pro (May) (Vertex)	2m	34	$2.19	66.2	0.42
Gemini 1.5 Pro (May) (AI Studio)	2m	34	$2.19	65.9	0.44
Qwen Turbo	1m	34	$0.09	99.8	1.10
Llama 3.2 90B (Vision)	128k	33	$0.72	57.8	0.37
Llama 3.2 90B (Vision) Vertex	128k	33	$0.00	32.7	0.19
Llama 3.2 90B (Vision)	128k	33	$0.90	42.2	0.40
Llama 3.2 90B (Vision)	33k	33	$0.36	33.7	0.47
Llama 3.2 90B (Vision)	8k	33	$0.90	263.6	0.33
Llama 3.2 90B (Vision) Turbo	128k	33	$1.20	34.1	0.32
Qwen2 72B	33k	33	$0.90	66.6	0.35
Nova Lite	300k	33	$0.10	285.9	0.33
Gemini 1.5 Flash-8B AI Studio	1m	31	$0.07	291.5	0.20
Jamba 1.5 Large	256k	29	$3.50	62.8	0.65
Jamba 1.5 Large	256k	29	$3.50	51.0	0.69
Jamba 1.6 Large	256k	29	$3.50	67.2	0.65
Gemini 1.5 Flash (May) (Vertex)	1m	28	$0.13	303.4	0.29
Gemini 1.5 Flash (May) (AI Studio)	1m	28	$0.13	298.8	0.21
Nova Micro	130k	28	$0.06	317.6	0.31
Yi-Large	32k	28	$3.00	68.8	0.46
Claude 3 Sonnet	200k	28	$6.00	50.4	0.77
Claude 3 Sonnet	200k	28	$6.00	59.4	0.56
Codestral (Jan '25)	256k	28	$0.45	205.8	0.31
Codestral (Jan '25) Vertex	128k	28	$0.45	155.3	0.16
Llama 3 70B	8k	27	$1.18	44.4	0.41
Llama 3 70B	8k	27	$0.40	23.6	1.26
Llama 3 70B	8k	27	$2.86	49.1	0.42
Llama 3 70B	8k	27	$2.90	18.9	0.77
Llama 3 70B	8k	27	$0.90	141.8	0.37
Llama 3 70B	8k	27	$0.27	42.9	0.40
Llama 3 70B	8k	27	$0.57	21.1	1.15
Llama 3 70B	8k	27	$0.64	331.5	0.25
Llama 3 70B (Reference, FP16)	8k	27	$0.90	151.1	0.50
Llama 3 70B (Turbo, FP8)	8k	27	$0.88	35.0	0.33
Mistral Small (Sep '24)	33k	27	$0.30	85.8	0.34
Phi-4 Multimodal	128k	27	$0.00	26.6	0.33
Qwen2.5 Coder 7B Fast	131k	27	$0.04	221.9	0.48
Qwen2.5 Coder 7B Base	131k	27	$0.01	195.4	0.51
Mistral Large (Feb '24)	33k	26	$6.00	31.7	0.49
Mistral Large (Feb '24)	33k	26	$6.00	41.2	0.39
Mistral Large (Feb '24)	33k	26	$6.00	39.9	0.49
Mixtral 8x22B	65k	26	$3.00	77.7	0.39
Mixtral 8x22B Base	65k	26	$0.60	89.3	0.54
Mixtral 8x22B Fast	65k	26	$1.05	104.6	0.55
Mixtral 8x22B	65k	26	$1.20	82.1	0.39
Mixtral 8x22B	65k	26	$1.20	70.6	0.45
Phi-4 Mini	128k	26	$0.12	201.3	0.43
Phi-4 Mini	128k	26	$0.00	52.6	0.34
Phi-3 Medium 14B	128k	25	$0.30	52.7	0.42
Claude 2.1	200k	24	$12.00	22.6	1.81
Claude 2.1	200k	24	$12.00	13.9	0.84
Llama 3.1 8B	128k	24	$0.03	133.0	0.41
Llama 3.1 8B	33k	24	$0.10	2,180.3	0.28
Llama 3.1 8B	128k	24	$0.10	70.6	0.90
Llama 3.1 8B	128k	24	$0.22	90.8	0.37
Llama 3.1 8B Fast	128k	24	$0.04	177.4	0.50
Llama 3.1 8B Base	128k	24	$0.03	66.2	0.54
Llama 3.1 8B Vertex	128k	24	$0.00	118.9	0.17
Llama 3.1 8B	128k	24	$0.38	221.1	0.29
Llama 3.1 8B	128k	24	$0.20	208.7	0.33
Llama 3.1 8B	128k	24	$0.04	55.1	0.51
Llama 3.1 8B	128k	24	$0.10	483.4	0.30
Llama 3.1 8B	16k	24	$0.05	67.3	0.74
Llama 3.1 8B	128k	24	$0.06	751.1	0.17
Llama 3.1 8B	16k	24	$0.13	1,076.6	0.24
Llama 3.1 8B Turbo	128k	24	$0.18	265.0	0.23
Llama 3.1 8B	128k	24	$0.15	460.5	0.18
Llama 3.1 8B	128k	24	$0.18	60.2	0.52
Pixtral 12B	128k	23	$0.15	105.3	0.34
Pixtral 12B	128k	23	$0.10	70.8	0.47
Mistral Small (Feb '24)	33k	23	$1.50	141.1	0.32
Mistral Small (Feb '24)	33k	23	$1.50	87.4	0.40
Mistral Medium	33k	23	$4.09	41.1	0.42
Ministral 8B	128k	22	$0.10	142.7	0.33
Gemma 2 9B Fast	8k	22	$0.04	172.0	0.52
Gemma 2 9B Base	8k	22	$0.03	166.0	0.52
Gemma 2 9B	8k	22	$0.04	49.3	0.33
Gemma 2 9B	8k	22	$0.20	652.8	0.22
Gemma 2 9B	8k	22	$0.30	130.6	0.23
LFM 40B	32k	22	$0.15	164.5	0.23
Command-R+	128k	21	$6.00	47.0	0.47
Command-R+	128k	21	$4.38	49.8	0.27
Llama 3 8B	8k	21	$0.10	75.2	0.40
Llama 3 8B	8k	21	$0.38	103.7	0.30
Llama 3 8B	8k	21	$0.38	73.6	0.38
Llama 3 8B	8k	21	$0.20	127.6	0.28
Llama 3 8B	8k	21	$0.04	110.0	0.52
Llama 3 8B	8k	21	$0.04	48.3	0.88
Llama 3 8B	8k	21	$0.06	1,198.3	0.30
Llama 3 8B	8k	21	$0.20	259.2	0.36
Gemini 1.0 Pro Vertex	33k	21	$0.19	161.3	0.40
Codestral (May '24)	33k	20	$0.30	105.6	0.35
Aya Expanse 32B	128k	20	$0.75	119.3	0.15
Command-R+ (Apr '24)	128k	20	$6.00	47.2	0.49
Command-R+ (Apr '24)	128k	20	$6.00	56.5	0.23
Command-R+ (Apr '24)	128k	20	$6.00	50.1	0.56
DBRX	33k	20	$1.13	69.2	0.49
Ministral 3B	128k	20	$0.04	222.8	0.33
Mistral NeMo	128k	20	$0.15	138.4	0.33
Mistral NeMo Fast	128k	20	$0.12	161.3	0.51
Mistral NeMo Base	128k	20	$0.06	23.8	0.66
Mistral NeMo	128k	20	$0.06	54.0	0.55
Llama 3.2 3B (FP8)	128k	20	$0.02	224.0	0.38
Llama 3.2 3B	128k	20	$0.10	164.8	0.69
Llama 3.2 3B	128k	20	$0.15	72.1	0.33
Llama 3.2 3B Base	128k	20	$0.01	123.6	0.50
Llama 3.2 3B	128k	20	$0.06	227.4	0.43
Llama 3.2 3B	128k	20	$0.10	166.2	0.25
Llama 3.2 3B	128k	20	$0.02	120.5	0.24
Llama 3.2 3B	32k	20	$0.04	77.3	0.69
Llama 3.2 3B	8k	20	$0.06	1,534.0	0.34
Llama 3.2 3B	8k	20	$0.10	1,529.6	0.21
Llama 3.2 3B Turbo	128k	20	$0.06	107.4	0.54
DeepSeek R1 Distill Qwen 1.5B	128k	19	$0.18	381.9	0.18
Jamba 1.5 Mini	256k	18	$0.25	170.8	0.46
Jamba 1.5 Mini	256k	18	$0.25	82.4	0.48
Jamba 1.6 Mini	256k	18	$0.25	197.1	0.44
Mixtral 8x7B	33k	17	$0.70	86.1	0.33
Mixtral 8x7B	33k	17	$0.51	59.9	0.33
Mixtral 8x7B Fast	33k	17	$0.23	162.2	0.51
Mixtral 8x7B Base	33k	17	$0.12	53.3	0.60
Mixtral 8x7B	33k	17	$0.50	177.7	0.28
Mixtral 8x7B	33k	17	$0.24	98.8	0.34
Mixtral 8x7B	33k	17	$0.63	94.0	0.45
Mixtral 8x7B	33k	17	$0.60	80.0	0.31
Aya Expanse 8B	8k	16	$0.75	165.7	0.12
Command-R	128k	15	$0.75	109.1	0.35
Command-R	128k	15	$0.26	63.0	0.19
Command-R (Mar '24)	128k	15	$0.75	108.3	0.35
Command-R (Mar '24)	128k	15	$0.75	116.3	0.16
Command-R (Mar '24)	128k	15	$0.75	80.7	0.44
Codestral-Mamba	256k	14	$0.25	95.5	0.49
Mistral 7B	8k	10	$0.25	112.6	0.34
Mistral 7B	8k	10	$0.16	92.9	0.32
Mistral 7B	8k	10	$0.04	81.1	0.37
Mistral 7B	32k	10	$0.06	104.3	0.80
Mistral 7B	8k	10	$0.20	169.2	0.19
Llama 3.2 1B	128k	10	$0.10	119.0	0.32
Llama 3.2 1B Base	128k	10	$0.01	268.5	0.47
Llama 3.2 1B	128k	10	$0.01	128.4	0.26
Llama 3.2 1B	8k	10	$0.04	3,285.6	0.46
Llama 3.2 1B	16k	10	$0.05	2,097.5	0.22
Llama 2 Chat 7B	4k	8	$0.10	124.1	0.52
o1-preview	128k		$26.25	134.8	28.54
o1-preview	128k		$28.88	121.2	32.02
GPT-4o (Aug '24)	128k		$4.38	127.0	0.42
GPT-4o (Aug '24)	128k		$4.38	82.8	0.85
GPT-4.5 (Preview)	128k		$93.75	12.8	1.33
o1-pro	200k		$262.50	25.2	106.12
Llama 3.2 11B (Vision)	128k		$0.16	142.6	0.34
Llama 3.2 11B (Vision)	128k		$0.15	83.8	0.44
Llama 3.2 11B (Vision)	128k		$0.20	106.4	0.29
Llama 3.2 11B (Vision)	128k		$0.06	50.4	0.50
Llama 3.2 11B (Vision)	8k		$0.18	749.7	0.16
Llama 3.2 11B (Vision) Turbo	128k		$0.18	155.6	0.20
Gemini 2.0 Flash (exp) (AI Studio)	1m		$0.00	249.6	0.24
Gemini 1.5 Flash (Sep) (Vertex)	1m		$0.13	186.7	0.23
Gemini 1.5 Flash (Sep) (AI Studio)	1m		$0.13	171.8	0.31
Gemma 2 27B Fast	8k		$0.26	85.9	0.56
Gemma 2 27B Base	8k		$0.15	53.3	0.58
Gemma 2 27B	8k		$0.80	89.8	0.29
Gemini 2.5 Pro Experimental	1m		$0.00	190.4	30.82
Claude 3.5 Sonnet (June)	200k		$6.00	44.6	1.09
Claude 3.5 Sonnet (June) Vertex	200k		$6.00	78.8	0.92
Claude 3.5 Sonnet (June)	200k		$6.00	79.5	0.83
Claude 3 Haiku	200k		$0.50	104.7	1.04
Claude 3 Haiku	200k		$0.50	139.4	0.73
Mistral Saba	32k		$0.30	100.9	0.40
Mistral Saba	32k		$0.79	388.5	0.34
DeepSeek Coder V2 Lite Fast, FP8	128k		$0.12	113.2	0.60
DeepSeek Coder V2 Lite Base, FP8	128k		$0.06	108.6	0.59
Sonar Reasoning	127k		$2.00	85.3	1.92
Solar Mini	4k		$0.15	47.4	1.05
Qwen1.5 Chat 110B	32k		$0.00	29.6	1.11
GPT-4 Turbo	128k		$15.00	30.7	0.83
GPT-4 Turbo	128k		$15.00	47.4	1.57
GPT-4	8k		$37.50	25.1	0.69
GPT-4o (ChatGPT)	128k		$7.50	103.0	0.47
Gemini 2.0 Flash-Lite (Preview) (AI Studio)	1m		$0.13	208.0	0.26
Claude 2.0	100k		$12.00	31.0	0.87
OpenChat 3.5	8k		$0.06	82.4	0.31
Jamba Instruct	256k		$0.55	169.3	0.43

Key definitions

Back to Navigation

Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).

Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.

Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).

Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.

Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.

Time period: Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.