Ollama Cloud Model Cost Table

Prices per 1M tokens for Ollama cloud models (run with the :cloud tag, e.g. ollama run deepseek-v4.1-flash:cloud). 17 models, sorted newest first. Click a column header to sort.

Model Peak ($ / 1M tokens) Off-Peak ($ / 1M tokens) Savings Context Size (params)
Input Cached Output Input Cached Output
deepseek-v4.1-flashcloudthinkingtoolsvision $0.30 $0.006 $1.20 $0.15 $0.003 $0.60 −50% 1M tokens 763B
glm-5.3-flashcloudthinkingtoolsvision $0.15 $0.03 $0.50 — — — — 1M tokens 321B
glm-5.3cloudthinkingtools $1.40 $0.26 $4.40 — — — — 1M tokens 753B
kimi-k3cloudthinkingtoolsvision $3.00 $0.30 $15.00 — — — — 1M tokens 2.81T
glm-5.2cloudthinkingtools $1.40 $0.26 $4.40 — — — — 976K tokens 756B
kimi-k2.7-codecloudthinkingtoolsvision $0.95 $0.19 $4.00 — — — — 256K tokens 1.04T
nemotron-3-ultracloudthinkingtools $0.10 $0.10 $3.00 — — — — 256K tokens 550B
minimax-m3cloudthinkingtoolsvision $0.60 $0.12 $2.40 — — — — 512K tokens —
deepseek-v4-procloudthinkingtools $1.32 $0.044 $3.96 $0.66 $0.022 $1.98 −50% 1M tokens 1.65T
kimi-k2.6cloudthinkingtoolsvision $0.95 $0.16 $4.00 — — — — 256K tokens 1.04T
minimax-m2.7cloudthinkingtools $0.30 $0.06 $1.20 — — — — 200K tokens 229B
gemma4cloudaudiothinkingtoolsvision $0.14 $0.05 $0.40 — — — — 256K tokens 32.7B
nemotron-3-supercloudthinkingtools $0.015 $0.015 $0.60 — — — — 256K tokens 120B
nemotron-3-nano:30b-cloud30b-cloudthinkingtools $0.06 — $0.24 — — — — 1M tokens 30B
mistral-large-3:675b-cloud675b-cloudtoolsvision $0.50 — $1.50 — — — — 256K tokens 675B
gpt-oss:120b-cloud120b-cloudthinkingtools $0.15 $0.014 $0.60 — — — — 128K tokens 120B
gpt-oss:20b-cloud20b-cloudthinkingtools $0.07 $0.035 $0.30 — — — — 128K tokens 20B

Cost by workload (peak)

Darker = more expensive within each workload column. Click a column header to load that workload into the calculator below.

Cost calculator

Presets:

Amounts accept K / M / G suffixes and commas, e.g. 2M or 500,000. Settings persist and are shareable via the URL hash. Ranks models matching the filter above.