moonshotai/kimi-k2.6
output price cut 20%, $3.42 → $2.72 per M tokens
meta-llama/llama-guard-4-12b
cheapest of 81 models at 1M+ context, $0.180 per M output
inclusionai/ling-2.6-flash
cheapest of 118 models at 200K+ context, $0.030 per M output
mistralai/mistral-nemo
cheapest of 83 models at 100K+ context, $0.030 per M output
mistralai/mistral-small-24b-instruct-2501
cheapest of 24 models at 32K+ context, $0.080 per M output
sao10k/l3-lunaris-8b
cheapest of 16 models at under 32K context, $0.050 per M output
deepseek/deepseek-v4-flash
2nd cheapest of 81 at 1M+ context, $0.188 per M output
nex-agi/nex-n2-mini
2nd cheapest of 118 at 200K+ context, $0.100 per M output
meta-llama/llama-3.1-8b-instruct
2nd cheapest of 83 at 100K+ context, $0.080 per M output
qwen/qwen-2.5-7b-instruct
2nd cheapest of 24 at 32K+ context, $0.100 per M output