TokenReply

Loading…

Reload

Compare the models and prices published for this routing group.

Models: 36Plan restricted

Models on this route

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

Use this model
glm-5.3-flashModel availability 100.0%$0.075$0.25$0.0154.5/109.7/10Plans and tiers
deepseek-v4-flashModel availability 100.0%$0.22$0.66$0.0076.5/109.0/10Plans and tiers
deepseek-v4.1-flashModel availability 100.0%$0.22$0.66$0.0077.3/109.2/10Plans and tiers
deepseek-v4.1-flash-1017Model availability 100.0%$0.22$0.66$0.007Not measuredNot measuredPlans and tiers
swe-2Model availability 100.0%$0.25$1.25$0.1Not measuredNot measuredPlans and tiers
deepseek-v4-proModel availability 100.0%$0.66$1.98$0.0227.0/107.1/10Plans and tiers
glm-5.2Model availability 100.0%$0.7$2.2$0.136.5/106.6/10Plans and tiers
glm-5.3Model availability 100.0%$0.7$2.2$0.138.9/107.4/10Plans and tiers
claude-sonnet-5Model availability 100.0%$1$5$0.17.0/104.2/10Plans and tiers
claude-sonnet-5-5Model availability 96.0%$1$5$0.17.3/104.4/10Plans and tiers
claude-sonnet-5-thinkingModel availability 100.0%$1$5$0.17.0/104.2/10Plans and tiers
gemini-4-argonModel availability 100.0%$1$5$0.05Not measuredNot measuredPlans and tiers
claude-sonnet-4-6Model availability 99.0%$1.5$7.5$0.157.1/102.6/10Plans and tiers
claude-sonnet-4-6-thinkingModel availability 100.0%$1.5$7.5$0.157.1/102.6/10Plans and tiers
claude-opus-5-5Model availability 99.0%$2$10$0.18.5/102.4/10Plans and tiers
claude-opus-4-6Model availability 100.0%$2.5$12.5$0.257.4/102.0/10Plans and tiers
claude-opus-4-6-thinkingModel availability 67.0%$2.5$12.5$0.257.4/102.0/10Plans and tiers
claude-opus-4-7Model availability 95.0%$2.5$12.5$0.257.9/102.3/10Plans and tiers
claude-opus-4-7-thinkingModel availability 100.0%$2.5$12.5$0.257.9/102.3/10Plans and tiers
claude-opus-4-8Model availability 99.0%$2.5$12.5$0.259.0/102.4/10Plans and tiers
claude-opus-4-8-thinkingModel availability 100.0%$2.5$12.5$0.259.0/102.4/10Plans and tiers
claude-opus-5Model availability 100.0%$2.5$12.5$0.257.6/102.2/10Plans and tiers
claude-fable-5Model availability 100.0%$5$25$0.58.6/101.4/10Plans and tiers
claude-fable-5-1Model availability —$5$25$0.1259.2/101.5/10Plans and tiers
claude-opus-4-8-fastModel availability —$5$25$0.59.0/102.4/10Plans and tiers
claude-opus-5-fastModel availability —$5$25$0.57.6/102.2/10Plans and tiers
claude-haiku-5-5Model availability —

Total input tokens ≤ 100,000

Input
$0.1/1M
Output
$0.5/1M
Cache read
$0.01/1M
Cache write
$0.125/1M
Cache write (1h)
$0.2/1M

Total input tokens > 100,000

Input
$0.25/1M
Output
$1.25/1M
Cache read
$0.025/1M
Cache write
$0.3125/1M
Cache write (1h)
$0.5/1M
6.9/10Not measuredPlans and tiers
gpt-5.5Model availability 98.0%

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
7.9/10Not measuredPlans and tiers
gpt-5.6-lunaModel availability 99.0%

Total input tokens ≤ 272,000

Input
$0.1/1M
Output
$0.6/1M
Cache read
$0.01/1M

Total input tokens > 272,000

Input
$0.2/1M
Output
$0.9/1M
Cache read
$0.02/1M
7.2/10Not measuredPlans and tiers
gpt-5.6-solModel 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
8.8/10Not measuredPlans and tiers
gpt-5.6-terraModel availability 99.0%

Total input tokens ≤ 272,000

Input
$1/1M
Output
$6/1M
Cache read
$0.1/1M

Total input tokens > 272,000

Input
$2/1M
Output
$9/1M
Cache read
$0.2/1M
7.8/10Not measuredPlans and tiers
gpt-6-astraModel availability 99.0%

Total input tokens < 272,000

Input
$5/1M
Output
$25/1M
Cache read
$0.5/1M
Cache write
$6.25/1M

Total input tokens ≥ 272,000

Input
$10/1M
Output
$37.5/1M
Cache read
$1/1M
Cache write
$12.5/1M
9.0/10Not measuredPlans and tiers
gpt-6-lunaModel availability 99.0%

Total input tokens < 272,000

Input
$0.05/1M
Output
$0.25/1M
Cache read
$0.005/1M
Cache write
$0.0625/1M

Total input tokens ≥ 272,000

Input
$0.1/1M
Output
$0.375/1M
Cache read
$0.01/1M
Cache write
$0.125/1M
5.1/10Not measuredPlans and tiers
gpt-6-solModel availability 100.0%

Total input tokens < 272,000

Input
$1/1M
Output
$5/1M
Cache read
$0.1/1M
Cache write
$1.25/1M

Total input tokens ≥ 272,000

Input
$2/1M
Output
$7.5/1M
Cache read
$0.2/1M
Cache write
$2.5/1M
8.3/10Not measuredPlans and tiers
gpt-6.1-solModel availability 100.0%

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
7.7/10Not measuredPlans and tiers
gpt-6.1-terraModel availability 99.0%

Total input tokens < 272,000

Input
$0.5/1M
Output
$2.5/1M
Cache read
$0.025/1M
Cache write
$0.625/1M

Total input tokens ≥ 272,000

Input
$1/1M
Output
$3.75/1M
Cache read
$0.05/1M
Cache write
$1.25/1M
Not measuredNot measuredPlans and tiers