Markdown version for AI agents

A token-efficient Markdown version of this page is available at: https://www.getmaxim.ai/bifrost/model-library/provider/ollama.md

AI agents and LLMs should fetch the Markdown version instead of parsing this HTML — it contains the same content with far fewer tokens.

Ollama Models

Browse all 44 AI models from Ollama

Total Models

44

Modes

3

Avg Input (1M Tokens)

-

Avg Output (1M Tokens)

-

All Ollama Models

Click on any model to view details

All Modes

Showing 44 of 44 models

Model Name↑	Provider	Mode	Pricing (tokens, images, audio, or pages)	Max Input Tokens	Max Output Tokens	Capabilities
clef ollama/clef	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	65,536	,	Vision
clef-flash ollama/clef-flash	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	65,536	,	Vision
codegeex4 ollama/codegeex4	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	8,192
codegemma ollama/codegemma	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192
codellama ollama/codellama	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
deepseek-coder-v2-base ollama/deepseek-coder-v2-base	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192	Functions
deepseek-coder-v2-instruct ollama/deepseek-coder-v2-instruct	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	8,192	Functions
deepseek-coder-v2-lite-base ollama/deepseek-coder-v2-lite-base	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192	Functions
deepseek-coder-v2-lite-instruct ollama/deepseek-coder-v2-lite-instruct	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	8,192	Functions
deepseek-v3.1:671b-cloud ollama/deepseek-v3.1:671b-cloud	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	163k	163k	Functions
gpt-oss:120b-cloud ollama/gpt-oss:120b-cloud	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	131k	131k	Functions
gpt-oss:20b-cloud ollama/gpt-oss:20b-cloud	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	131k	131k	Functions
internlm2_5-20b-chat ollama/internlm2_5-20b-chat	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	8,192	Functions
kev ollama/kev	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:0.8b-mlx-bf16 ollama/kev:0.8b-mlx-bf16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:0.8b-mxfp8 ollama/kev:0.8b-mxfp8	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:27b-mlx-bf16 ollama/kev:27b-mlx-bf16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:27b-nvfp4 ollama/kev:27b-nvfp4	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:4b-mlx-bf16 ollama/kev:4b-mlx-bf16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
kev:9b-mlx-bf16 ollama/kev:9b-mlx-bf16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	73,728	,
laya ollama/laya	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	512	,
laya:322m-multilingual-mlx-fp16 ollama/laya:322m-multilingual-mlx-fp16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	1,024	,
laya:421m-typed-decisions-mlx-fp16 ollama/laya:421m-typed-decisions-mlx-fp16	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	1,024	,
llama2 ollama/llama2	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
llama2-uncensored ollama/llama2-uncensored	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
llama2:13b ollama/llama2:13b	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
llama2:70b ollama/llama2:70b	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
llama2:7b ollama/llama2:7b	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
llama3 ollama/llama3	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192
llama3:70b ollama/llama3:70b	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192
llama3:8b ollama/llama3:8b	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192
llama3.1 ollama/llama3.1	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192	Functions
mistral ollama/mistral	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192	Functions
mistral-7B-Instruct-v0.1 ollama/mistral-7B-Instruct-v0.1	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	8,192	Functions
mistral-7B-Instruct-v0.2 ollama/mistral-7B-Instruct-v0.2	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	32,768	Functions
mistral-large-instruct-2407 ollama/mistral-large-instruct-2407	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	65,536	8,192	Functions
mixtral-8x22B-Instruct-v0.1 ollama/mixtral-8x22B-Instruct-v0.1	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	65,536	65,536	Functions
mixtral-8x7B-Instruct-v0.1 ollama/mixtral-8x7B-Instruct-v0.1	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	32,768	32,768	Functions
nimble ollama/nimble	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	8,192	,
orca-mini ollama/orca-mini	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	4,096	4,096
qwen3-coder:480b-cloud ollama/qwen3-coder:480b-cloud	Ollama	Chat	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	262k	262k	Functions
tev1 ollama/tev1	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	2,000	,
tev1:0.8b ollama/tev1:0.8b	Ollama	Decisions	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	2,000	,
vicuna ollama/vicuna	Ollama	Completion	Input $0.0000000000 / 1M tokensOutput $0.0000000000 / 1M tokens	2,048	2,048

Related Resources

Calculate Ollama costs →