Ollama API pricing

Model AggregatorCoding Tool

Ollama runs open models locally and, through Ollama Cloud, hosts them behind an API (native, OpenAI- and Anthropic-compatible) billed per token in USD, with off-peak rates on some models. Its Pro, Max and Team subscriptions are a monthly fee bundling dollars of usage credits spent at the same per-token rates.

Compare the published API prices listed for Ollama. Open a model for its available pricing tiers, source and conditions, or use the cost planner to estimate your own workload.

Models

Prompt Caching

✓

Batch Discount

—

Tool Calling

—

Visit Website →View Official Pricing →

Model28

					Modality
beam	$0.125	$0.4	$0.015	—	text
clef	$0.24	—	—	—	text
deepseek-v4-flashDeepSeek	Standard$0.44 Off-peak$0.22	$1.32 $0.66	$0.014 $0.007	—	text
deepseek-v4-proDeepSeek	Standard$1.32 Off-peak$0.66	$3.96 $1.98	$0.044 $0.022	—	text
deepseek-v4.1-flashDeepSeek	Standard$0.3 Off-peak$0.15	$1.2 $0.6	$0.006 $0.003	—	text
gemma4Gemma	$0.14	$0.4	$0.05	—	text
glm-5.1GLM	$1	$3.2	$0.2	—	text
glm-5.2GLM	$1.4	$4.4	$0.26	—	text
glm-5.3GLM	$1.4	$4.4	$0.26	—	text
glm-5.3-flashGLM	$0.15	$0.5	$0.03	—	text
gpt-oss:120bGPT-OSS	$0.15	$0.6	$0.014	—	text
gpt-oss:20bGPT-OSS	$0.07	$0.3	$0.035	—	text
kimi-k2.6Kimi	$0.95	$4	$0.16	—	text
kimi-k2.7-codeKimi	$0.95	$4	$0.19	—	text
kimi-k3Kimi	$3	$15	$0.3	—	text
kimi-k3.1-proKimi	$2	$10	$0.2	—	text
mimo-v2.6-flash	$0.14	$0.28	$0.0028	—	text
mimo-v2.6-pro	$0.435	$0.87	$0.0036	—	text
minimax-m2.7MiniMax	$0.3	$1.2	$0.06	—	text
minimax-m3MiniMax	$0.6	$2.4	$0.12	—	text
minimax-m3.1-flashMiniMax	$0.15	$0.6	$0.015	—	text
mistral-large-3Mistral	$0.5	$1.5	—	—	text
mistral-large-4Mistral	$0.7	$2.1	$0.07	—	text
muse-spark-open	$1.25	$4.25	$0.15	—	text
nemotron-3-nanoNemotron	$0.06	$0.24	—	—	text
nemotron-3-superNemotron	$0.015	$0.6	$0.015	—	text
nemotron-3-ultraNemotron	$0.1	$3	$0.1	—	text
qwen3.5:397bQwen	$0.6	$3.6	—	—	text

Ollama API cost examples

1,000 requests, each using 1,000 input tokens and 200 billed text output tokens: 1M input and 200K output tokens in total.

Standard text token prices and estimated workload cost in USD
Model	Input / 1M tokens	Output / 1M tokens	Estimated cost	Pricing conditions
nemotron-3-nanoOllama	$0.06	$0.24	$0.108	Region not specifiedView official pricing
gpt-oss:20bOllama	$0.07	$0.3	$0.13	Region not specifiedView official pricing
nemotron-3-superOllama	$0.015	$0.6	$0.135	Region not specifiedView official pricing
mimo-v2.6-flashOllama	$0.14	$0.28	$0.196	Region not specifiedView official pricing
beamOllama	$0.125	$0.4	$0.205	Region not specifiedView official pricing
gemma4Ollama	$0.14	$0.4	$0.22	Region not specifiedView official pricing

Estimates in USD use standard processing, uncached input and the displayed base input tier. Regional rates, longer prompts, thinking tokens and other billable usage can change the final cost. Models can differ in capabilities.

Calculate costs for your workload →

Coding subscription

Compare against other vendors

What this vendor sells as a flat monthly plan, and what each tier grants. Equivalent API value prices the allowance at this vendor's own API rates.

Plan	Price / month	Equivalent API value	Value multiple	Main allowance	Models	When it runs out
Ollama$20–$5005 plans
Ollama Free Official page API use authorized	$0	Vendor publishes no figure	—	usd_pool/month Allowance not published starter usage credits, amount not published	Starter models	Use any cloud model with pay-as-you-go usage credits
Ollama Pro Official page API use authorized	$20 $17 billed annually	$60 Priced on deepseek-v4.1-flash	3.00×	usd_pool/month 60 USD of usage credits per month	deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17	draws from the purchased usage credit balance at each model's per-token rate
Ollama Max Official page API use authorized	$100	$300 Priced on deepseek-v4.1-flash	3.00×	usd_pool/month 300 USD of usage credits per month	deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17	draws from the purchased usage credit balance at each model's per-token rate
Ollama Team Official page API use authorized	$500	$1,000 Priced on deepseek-v4.1-flash	2.00×	usd_pool/month 1000 USD of usage credits per month, shared across the team	deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17	draws from a shared team balance billed as you go
Ollama Enterprise Official page API use authorized	Contact sales — excluded from ranking	Contact sales — excluded from ranking	—	usd_pool/month Allowance not published volume usage pricing, allowance not published	deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17	—

Ollama$20–$5005 plans

Ollama Free

Value multiple—Vendor publishes no figure

usd_pool/month Allowance not published starter usage credits, amount not published

Starter models

API use authorized

Ollama Pro

$20

$17 billed annually

Value multiple3.00×

$60

Priced on deepseek-v4.1-flash

usd_pool/month 60 USD of usage credits per month

deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17

API use authorized

Ollama Max

$100

Value multiple3.00×

$300

Priced on deepseek-v4.1-flash

usd_pool/month 300 USD of usage credits per month

deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17

API use authorized

Ollama Team

$500

Value multiple2.00×

$1,000

Priced on deepseek-v4.1-flash

usd_pool/month 1000 USD of usage credits per month, shared across the team

deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17

API use authorized

Ollama Enterprise

Contact sales — excluded from ranking

Value multiple—Contact sales — excluded from ranking

usd_pool/month Allowance not published volume usage pricing, allowance not published

deepseek-v4.1-flashdeepseek-v4-flashdeepseek-v4-pro+17

API use authorized