Ollama LLM API pricing

Every model Ollama serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

29

on this provider

Cheapest input

$0.00

per 1M tokens

Cheapest output

$0.00

per 1M tokens

Max context

262K

tokens

Model ID
CodellamaMeta4K$0.00$0.00ollama/codellama
DeepSeek Coder V2 BaseDeepSeek8K$0.00$0.00ollama/deepseek-coder-v2-base
DeepSeek Coder V2 InstructDeepSeek66K$0.00$0.00ollama/deepseek-coder-v2-instruct
DeepSeek Coder V2 Lite BaseDeepSeek164K$0.00$0.00ollama/deepseek-coder-v2-lite-base
GPT OSS 120B CloudOpenAI131K$0.00$0.00ollama/gpt-oss:120b-cloud
GPT OSS 20B CloudOpenAI131K$0.00$0.00ollama/gpt-oss:20b-cloud
internlm2_5-20b-chatOther33K$0.00$0.00ollama/internlm2_5-20b-chat
Llama2 UncensoredMeta4K$0.00$0.00ollama/llama2-uncensored
Llama2 13BMeta4K$0.00$0.00ollama/llama2:13b
Llama2 70BMeta4K$0.00$0.00ollama/llama2:70b
Llama2 7BMeta4K$0.00$0.00ollama/llama2:7b
Llama3Meta8K$0.00$0.00ollama/llama3
Llama3 70BMeta8K$0.00$0.00ollama/llama3:70b
Llama3 8BMeta8K$0.00$0.00ollama/llama3:8b
Mistral 7B Instruct V0 1Mistral16K$0.00$0.00ollama/mistral-7B-Instruct-v0.1
Llama2Meta4K$0.00$0.00ollama/llama2
Mistral 7B Instruct V0 2Mistral33K$0.00$0.00ollama/mistral-7B-Instruct-v0.2
Mistral Large Instruct 2407Mistral66K$0.00$0.00ollama/mistral-large-instruct-2407
Mixtral 8x22B Instruct V0 1Mistral66K$0.00$0.00ollama/mixtral-8x22B-Instruct-v0.1
Mixtral 8x7B Instruct V0 1Mistral33K$0.00$0.00ollama/mixtral-8x7B-Instruct-v0.1
Qwen3 Coder 480B CloudAlibaba262K$0.00$0.00ollama/qwen3-coder:480b-cloud
Codegeex4Other33K$0.00$0.00ollama/codegeex4
DeepSeek V3 1 671B CloudDeepSeek164K$0.00$0.00ollama/deepseek-v3.1:671b-cloud
MistralMistral8K$0.00$0.00ollama/mistral
DeepSeek Coder V2 Lite InstructDeepSeek164K$0.00$0.00ollama/deepseek-coder-v2-lite-instruct
Orca MiniOther4K$0.00$0.00ollama/orca-mini
Llama3 1Meta8K$0.00$0.00ollama/llama3.1
CodegemmaGoogle8K$0.00$0.00ollama/codegemma
VicunaOther2K$0.00$0.00ollama/vicuna
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI