# Together

HQ US · serves 32 tracked open-weights models. status page · privacy policy

models
32
verified
of overall top 10
8
cheapest on
1 models
vs best $
1.71×
ctx (median)
256k
uptime
99.0%

# models

model rank $/M in $/M out $/M cache src
kimi-k3 #1 $3.00 $15.00 $0.30 openrouter
deepseek-v4-pro #2 $1.74 $3.48 $0.20 modelsdev
glm-5.2 #3 $1.40 $4.40 $0.26 openrouter
kimi-k2.6 #4 $1.20 $4.50 $0.20 modelsdev
minimax-m3 #6 $0.30 $1.20 $0.06 openrouter
kimi-k2.7-code #7 $0.95 $4.00 $0.19 openrouter
glm-5 #9 $1.00 $3.20 modelsdev
glm-5.1 #10 $1.40 $4.40 $0.26 modelsdev
minimax-m2.5 #11 $0.30 $1.20 $0.06 modelsdev
kimi-k2.5 #12 $0.50 $2.80 modelsdev
glm-4.7 #15 $0.45 $2.00 litellm
qwen3.5-397b-a17b #17 $0.60 $3.60 $0.35 modelsdev
kimi-k2-0905 #22 $1.00 $3.00 litellm
glm-4.6 #24 $0.60 $2.20 litellm
gemma-4-31b-it #25 $0.39 $0.97 openrouter
qwen3-coder-480b-a35b #32 $2.00 $2.00 modelsdev
deepseek-r1 #33 $3.00 $7.00 modelsdev
gpt-oss-120b #35 $0.15 $0.60 openrouter
kimi-k2-instruct #36 $1.00 $3.00 litellm
deepseek-v3.1 #37 $0.60 $1.70 litellm
deepseek-v3 #42 $1.25 $1.25 modelsdev
deepseek-v4-flash-0731 $0.14 $0.28 $0.03 openrouter
gpt-oss-20b $0.05 $0.20 openrouter
inkling $1.00 $4.05 $0.17 openrouter
llama-3.3-70b-instruct $1.04 $1.04 openrouter
llama-4-scout $0.18 $0.59 litellm
minimax-m2.7 $0.30 $1.20 $0.06 modelsdev
muse-glimmer-30b $0.35 $1.50 $0.04 openrouter
qwen3-coder-next $0.50 $1.20 modelsdev
qwen3-next-80b-a3b-thinking $0.15 $1.50 litellm
qwen3.5-9b $0.17 $0.25 openrouter
qwen3.8-2.4t-a95b $2.00 $6.00 $0.25 openrouter

# recent changes

when (UTC)modelchange
Sep 4 04:45 qwen3.8-2.4t-a95b $/M input $2.50 → $2.00 ↓ 20.0%
Sep 4 04:45 qwen3.8-2.4t-a95b $/M output $6.25 → $6.00 ↓ 4.0%

all providers · machine-readable: providers.json