# Together

HQ US · serves 48 tracked open-weights models. status page · privacy policy

models
48
verified
—
of overall top 10
6
cheapest on
3 models
vs best $
2.25×
ctx (median)
256k
uptime
100.0%

# models

model rank $/M in $/M out $/M cache src ✓
glm-5.3 #1 $1.40 $4.40 $0.26 openrouter —
kimi-k3 #2 $3.00 $15.00 $0.30 openrouter —
glm-5.3-flash #3 $0.15 $0.50 $0.03 openrouter —
qwen3.8-2.4t-a95b #4 $2.00 $6.00 $0.25 openrouter —
deepseek-v4-flash-0731 #6 $0.14 $0.28 $0.03 modelsdev —
glm-5.2 #10 $1.40 $4.40 $0.26 openrouter —
minimax-m3 #12 $0.30 $1.20 $0.06 openrouter —
glm-5 #14 $1.00 $3.20 — modelsdev —
kimi-k2.6 #15 $1.20 $4.50 — litellm —
glm-5.1 #18 $1.40 $4.40 $0.26 modelsdev —
kimi-k2.7-code #19 $0.95 $4.00 — litellm —
minimax-m2.5 #20 $0.30 $1.20 $0.06 modelsdev —
inkling #21 $1.00 $4.05 $0.17 openrouter —
minimax-m2.7 #25 $0.30 $1.20 $0.06 modelsdev —
glm-4.7 #28 $0.45 $2.00 — litellm —
qwen3.5-397b-a17b #31 $0.60 $3.60 $0.35 modelsdev —
glm-4.6 #40 $0.60 $2.20 — litellm —
gemma-4-31b-it #49 $0.39 $0.97 — litellm —
qwen3.5-9b #54 $0.17 $0.25 — openrouter —
deepseek-r1 #55 $3.00 $7.00 — modelsdev —
deepseek-v3.1 #57 $0.60 $1.70 — litellm —
qwen3-coder-480b-a35b #60 $2.00 $2.00 — modelsdev —
kimi-k2-instruct #61 $1.00 $3.00 — litellm —
gpt-oss-120b #63 $0.15 $0.60 — openrouter —
qwen3-coder-next #72 $0.50 $1.20 — modelsdev —
gpt-oss-20b #75 $0.05 $0.20 — litellm —
deepseek-v3 #77 $1.25 $1.25 — modelsdev —
qwq-32b #85 $1.20 $1.20 — litellm —
qwen3-vl-32b-instruct #89 $0.50 $1.50 — litellm —
nvidia-nemotron-nano-9b-v2 #93 $0.06 $0.25 — litellm —
qwen2.5-72b-instruct #99 $1.20 $1.20 — litellm —
llama-4-scout #103 $0.18 $0.59 — litellm —
qwen3-vl-8b-instruct #104 $0.18 $0.68 — litellm —
beam-1.0-501b-a23b — $0.40 $1.20 $0.04 openrouter —
deepseek-r1-0528 — $3.00 $7.00 — litellm —
deepseek-v4-pro-0813 — $1.32 $3.96 $0.13 openrouter —
deepseek-v4.1-flash — $0.30 $1.20 $0.01 openrouter —
deepseek-v4.1-flash-1017 — $0.30 $1.20 $0.01 openrouter —
llama-3.1-405b-instruct — $3.50 $3.50 — litellm —
minimax-m3.1-flash — $0.15 $0.60 $0.01 openrouter —
ministral-14b-2512 — $0.20 $0.20 — litellm —
muse-glimmer-30b — $0.35 $1.50 $0.04 openrouter —
muse-spark-open — $1.25 $4.25 $0.15 openrouter —
nemotron-3-ultra-550b-a55b — $0.60 $3.60 $0.20 modelsdev —
nemotron-3.5-super-vl — $0.15 $0.50 $0.02 openrouter —
qwen2.5-coder-32b — $0.80 $0.80 — litellm —
qwen2.5-vl-72b-instruct — $1.95 $8.00 — litellm —
qwen3-next-80b-a3b-thinking — $0.15 $1.50 — litellm —

# recent changes

when (UTC)modelchange
Oct 24 04:48 llama-3.3-70b-instruct no longer listed

all providers · machine-readable: providers.json