Default

Compare the models and prices published for this routing group.

Models on this route

Score

Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.

Sort by

						Use this model
gemini-2.5-flash-liteModel availability 100.0%	$0.1	$0.4	$0.01	2.8/10	8.8/10	Use this model
gemma-4-31b-itModel availability 54.0%	$0.14	$0.4	$0.014	6.7/10	9.6/10	Use this model
mimo-v2.5Model availability 65.0%	$0.14	$0.28	$0.0028	Not measured	Not measured	Use this model
mimo-v2.5-plusModel availability 25.0%	$0.14	$0.28	$0.0028	Not measured	Not measured	Use this model
mimo-v2.6-flashModel availability 100.0%	$0.14	$0.28	$0.0028	Not measured	Not measured	Use this model
glm-5.3-flashModel availability 100.0%	$0.15	$0.5	$0.03	4.5/10	9/10	Use this model
gemini-3.1-flash-liteModel availability 100.0%	$0.25	$1.5	$0.025	Not measured	Not measured	Use this model
deepseek-v3.2Model availability 100.0%	$0.26	$0.38	$0.13	6.2/10	9.4/10	Use this model
deepseek-v3.2-thinkingModel availability 100.0%	$0.26	$0.38	$0.13	6.2/10	9.4/10	Use this model
gemini-2.5-flashModel availability 100.0%	$0.3	$2.5	$0.03	Not measured	Not measured	Use this model
minimax-m2.1Model availability —	$0.3	$1.2	$0.03	Not measured	Not measured	Use this model
minimax-m2.1-thinkingModel availability —	$0.3	$1.2	$0.03	Not measured	Not measured	Use this model
minimax-m2.5Model availability 100.0%	$0.3	$1.2	$0.03	6.3/10	8.4/10	Use this model
minimax-m2.5-thinkingModel availability —	$0.3	$1.2	$0.03	6.3/10	8.4/10	Use this model
minimax-m2.7Model availability —	$0.3	$1.2	$0.06	Not measured	Not measured	Use this model
qwen3.7-plusModel availability 100.0%	$0.4	$1.6	$0.08	Not measured	Not measured	Use this model
mimo-v2.5-proModel availability 50.0%	$0.435	$0.87	$0.0036	6.9/10	8.8/10	Use this model
mimo-v2.5-pro-plusModel availability 0.0%	$0.435	$0.87	$0.0036	Not measured	Not measured	Use this model
mimo-v2.6-proModel availability 100.0%	$0.435	$0.87	$0.0036	Not measured	Not measured	Use this model
deepseek-v4-flashModel availability 99.0%	$0.44	$1.32	$0.014	6.5/10	8/10	Use this model
deepseek-v4-flash-0731Model availability 99.0%	$0.44	$1.32	$0.014	7.2/10	8.1/10	Use this model
deepseek-v4-flash-thinkingModel availability 99.0%	$0.44	$1.32	$0.014	6.5/10	8/10	Use this model
deepseek-v4.1-flashModel availability 100.0%	$0.44	$1.32	$0.014	7.3/10	8.2/10	Use this model
deepseek-v4.1-flash-1017Model availability 99.0%	$0.44	$1.32	$0.014	Not measured	Not measured	Use this model
gemini-3-flashModel availability 100.0%	$0.5	$3	$0.05	Not measured	Not measured	Use this model
gemini-3-flash-previewModel availability 100.0%	$0.5	$3	$0.05	6.7/10	6.3/10	Use this model
nemotron-3-superModel availability —	$0.6	$2.4	—	Not measured	Not measured	Use this model
nemotron-3-ultraModel availability 95.0%	$0.6	$2.4	$0.12	Not measured	Not measured	Use this model
gemini-3.8-flashModel availability 97.0%	$0.75	$3.75	$0.075	8.4/10	6.2/10	Use this model
kimi-k2.6Model availability 100.0%	$0.95	$4	$0.16	6.8/10	5.2/10	Use this model
kimi-k2.7Model availability 100.0%	$0.95	$4	$0.19	Not measured	Not measured	Use this model
kimi-k2.7-codeModel availability 100.0%	$0.95	$4	$0.19	5.6/10	4.5/10	Use this model
claude-haiku-4-5Model availability 95.0%	$1	$5	$0.1	6.5/10	4.1/10	Use this model
claude-haiku-4-5-thinkingModel availability 93.0%	$1	$5	$0.1	6.5/10	4.1/10	Use this model
glm-5Model availability 100.0%	$1	$3.2	$0.2	7.3/10	6.1/10	Use this model
glm-5-thinkingModel availability 100.0%	$1	$3.2	$0.2	7.3/10	6.1/10	Use this model
deepseek-v4-proModel availability 100.0%	$1.32	$3.96	$0.044	7/10	5/10	Use this model
deepseek-v4-pro-0813Model availability 100.0%	$1.32	$3.96	$0.044	8.2/10	5.9/10	Use this model
deepseek-v4-pro-thinkingModel availability 99.0%	$1.32	$3.96	$0.044	7/10	5/10	Use this model
glm-5.2Model availability 100.0%	$1.4	$4.4	$0.26	6.5/10	4.2/10	Use this model
glm-5.3Model availability 100.0%	$1.4	$4.4	$0.26	8.9/10	5.7/10	Use this model
gemini-3.5-flashModel availability 50.0%	$1.5	$9	$0.15	7.9/10	2.9/10	Use this model
grok-4.7Model availability —	$2	$6	$0.5	8.8/10	4.1/10	Use this model
kimi-k3.1-proModel availability 100.0%	$2	$10	$0.2	Not measured	Not measured	Use this model
qwen3.7-maxModel availability 100.0%	$2.5	$7.5	$0.5	7.9/10	3.1/10	Use this model
claude-sonnet-4-5Model availability 96.0%	$3	$15	$0.3	7.6/10	2/10	Use this model
claude-sonnet-4-5-thinkingModel availability 94.0%	$3	$15	$0.3	7.6/10	2/10	Use this model
claude-sonnet-4-6Model availability 97.0%	$3	$15	$0.3	7.1/10	1.9/10	Use this model
claude-sonnet-4-6-thinkingModel availability 94.0%	$3	$15	$0.3	7.1/10	1.9/10	Use this model
kimi-k3Model availability 99.0%	$3	$15	$0.3	8.9/10	2.3/10	Use this model
claude-opus-4-6Model availability 96.0%	$5	$25	$0.5	7.4/10	1.3/10	Use this model
claude-opus-4-6-thinkingModel availability 63.0%	$5	$25	$0.5	7.4/10	1.3/10	Use this model
big-pickle-freeModel availability 9.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
big-pickle-thinking-freeModel availability 7.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
dots-3-note-previewModel availability 100.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
google/diffusiongemma-26b-a4b-itModel availability 47.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
google/gemma-4-31b-itModel availability 4.0%	$0.00Per request	—	—	6.7/10	Not measured	Use this model
grok-4.20-fastModel availability 100.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
laguna-s-2.1Model availability 66.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
laguna-xs-2.1Model availability 46.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
lfm-2.5-2.6bModel availability 39.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
meta/llama-3.2-11b-vision-instructModel availability 96.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
meta/llama-3.2-90b-vision-instructModel availability 1.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
meta/muse-glimmer-30bModel availability 94.0%	$0.00Per request	—	—	8.3/10	Not measured	Use this model
mimo-v2.6-flash-freeModel availability 7.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
mimo-v2.6-flash-thinking-freeModel availability 7.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
minimax-m3.1-flash-freeModel availability 0.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3-nano-omni-30b-a3b-reasoningModel availability 72.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3-ultra-freeModel availability 0.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3-ultra-thinking-freeModel availability 0.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3.5-lightning-freeModel availability 52.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3.5-lightning-thinking-freeModel availability 5.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nemotron-3.5-super-vl-freeModel availability 92.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
north-mini-codeModel availability 100.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nvidia/ising-calibration-1.5-31bModel availability 87.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nvidia/nemotron-3-super-120b-a12bModel availability 0.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
nvidia/nemotron-3-ultra-550b-a55bModel availability 95.0%	$0.00Per request	—	—	4.9/10	Not measured	Use this model
nvidia/nemotron-3.5-lightning-30b-a3bModel availability 100.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
openai/gpt-oss-20bModel availability 68.0%	$0.00Per request	—	—	3.9/10	Not measured	Use this model
riva-translate-4b-instruct-v2Model availability 100.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
step-5-previewModel availability 87.0%	$0.00Per request	—	—	Not measured	Not measured	Use this model
z-ai/glm-5.3Model availability 33.0%	$0.00Per request	—	—	8.9/10	Not measured	Use this model
z-ai/glm-5.3-flashModel availability 15.0%	$0.00Per request	—	—	4.5/10	Not measured	Use this model
grok-imagine-imageModel availability —	$0.02Per request	—	—	Not measured	Not measured	Use this model
gemini-3.1-flash-imageModel availability 66.0%	Base $0.14 1K $0.14 2K $0.21 4K $0.315 Size rates apply where resolution selection is supported; charged per image returned.			Not measured	Not measured	Use this model
gpt-5.4Model availability 99.0%	Total input tokens ≤ 272,000 Input $2.5/1M Output $15/1M Cache read $0.25/1M Total input tokens > 272,000 Input $5/1M Output $22.5/1M Cache read $0.5/1M			8.6/10	Not measured	Use this model
gpt-5.5Model availability 98.0%	Total input tokens ≤ 272,000 Input $5/1M Output $30/1M Cache read $0.5/1M Total input tokens > 272,000 Input $10/1M Output $45/1M Cache read $1/1M			7.9/10	Not measured	Use this model
gpt-5.6-lunaModel availability 100.0%	Total input tokens ≤ 272,000 Input $0.2/1M Output $1.2/1M Cache read $0.02/1M Total input tokens > 272,000 Input $0.4/1M Output $1.8/1M Cache read $0.04/1M			7.2/10	Not measured	Use this model
gpt-5.6-solModel availability 100.0%	Total input tokens ≤ 272,000 Input $5/1M Output $30/1M Cache read $0.5/1M Total input tokens > 272,000 Input $10/1M Output $45/1M Cache read $1/1M			8.8/10	Not measured	Use this model
gpt-5.6-terraModel availability 100.0%	Total input tokens ≤ 272,000 Input $2/1M Output $12/1M Cache read $0.2/1M Total input tokens > 272,000 Input $4/1M Output $18/1M Cache read $0.4/1M			7.8/10	Not measured	Use this model
gpt-6-astraModel availability 100.0%	Total input tokens < 272,000 Input $10/1M Output $50/1M Cache read $1/1M Cache write $12.5/1M Total input tokens ≥ 272,000 Input $20/1M Output $75/1M Cache read $2/1M Cache write $25/1M			9/10	Not measured	Use this model
gpt-6-lunaModel availability 100.0%	Total input tokens < 272,000 Input $0.1/1M Output $0.5/1M Cache read $0.01/1M Cache write $0.125/1M Total input tokens ≥ 272,000 Input $0.2/1M Output $0.75/1M Cache read $0.02/1M Cache write $0.25/1M			5.1/10	Not measured	Use this model
gpt-6-solModel availability 100.0%	Total input tokens < 272,000 Input $2/1M Output $10/1M Cache read $0.2/1M Cache write $2.5/1M Total input tokens ≥ 272,000 Input $4/1M Output $15/1M Cache read $0.4/1M Cache write $5/1M			8.3/10	Not measured	Use this model
gpt-6.1-solModel availability 100.0%	Total input tokens < 272,000 Input $2/1M Output $10/1M Cache read $0.1/1M Cache write $2.5/1M Total input tokens ≥ 272,000 Input $4/1M Output $15/1M Cache read $0.2/1M Cache write $5/1M			7.7/10	Not measured	Use this model
gpt-6.1-terraModel availability 93.0%	Total input tokens < 272,000 Input $1/1M Output $5/1M Cache read $0.05/1M Cache write $1.25/1M Total input tokens ≥ 272,000 Input $2/1M Output $7.5/1M Cache read $0.1/1M Cache write $2.5/1M			Not measured	Not measured	Use this model
grok-4.5Model availability —	Total input tokens < 200,000 Input $2/1M Output $6/1M Cache read $0.3/1M Total input tokens ≥ 200,000 Input $4/1M Output $12/1M Cache read $0.6/1M			7.5/10	Not measured	Use this model
grok-4.6Model availability 50.0%	Total input tokens < 200,000 Input $2/1M Output $6/1M Cache read $0.5/1M Total input tokens ≥ 200,000 Input $4/1M Output $12/1M Cache read $1/1M			9/10	Not measured	Use this model
minimax-m3Model availability 100.0%	Total input tokens ≤ 512,000 Input $0.3/1M Output $1.2/1M Cache read $0.06/1M Total input tokens > 512,000 Input $0.6/1M Output $2.4/1M Cache read $0.12/1M			5.5/10	Not measured	Use this model
nano-banana-2Model availability 65.0%	Base $0.14 1K $0.14 2K $0.21 4K $0.315 Size rates apply where resolution selection is supported; charged per image returned.			Not measured	Not measured	Use this model

TokenReply

Models on this route