21
Models Available
$0.000
Cheapest Input / 1M
262K
Largest Context
What is Ollama?
Ollama is an AI model provider offering 21 large language models for developers. Their cheapest model starts at $0.000 per 1M input tokens, and their largest context window reaches 262K. Ollama provides 21 AI models accessible via API.
Ollama Strengths
All Ollama Models
| Model | Input $/1M | Output $/1M | Context | Max Output | Released |
|---|---|---|---|---|---|
| Codegeex4 | $0.000 | $0.000 | 33K | 8,192 | — |
| Deepseek Coder V2 Instruct | $0.000 | $0.000 | 33K | 8,192 | — |
| Deepseek Coder V2 Lite Instruct | $0.000 | $0.000 | 33K | 8,192 | — |
| Deepseek V3.1:671b Cloud | $0.000 | $0.000 | 164K | 163,840 | — |
| Gpt Oss:120b Cloud | $0.000 | $0.000 | 131K | 131,072 | — |
| Gpt Oss:20b Cloud | $0.000 | $0.000 | 131K | 131,072 | — |
| Internlm2 5 20b Chat | $0.000 | $0.000 | 33K | 8,192 | — |
| Llama2 | $0.000 | $0.000 | 4K | 4,096 | — |
| Llama2:13b | $0.000 | $0.000 | 4K | 4,096 | — |
| Llama2:70b | $0.000 | $0.000 | 4K | 4,096 | — |
| Llama2:7b | $0.000 | $0.000 | 4K | 4,096 | — |
| Llama3 | $0.000 | $0.000 | 8K | 8,192 | — |
| Llama3.1 | $0.000 | $0.000 | 8K | 8,192 | — |
| Llama3:70b | $0.000 | $0.000 | 8K | 8,192 | — |
| Llama3:8b | $0.000 | $0.000 | 8K | 8,192 | — |
| Mistral 7B Instruct V0.1 | $0.000 | $0.000 | 8K | 8,192 | — |
| Mistral 7B Instruct V0.2 | $0.000 | $0.000 | 33K | 32,768 | — |
| Mistral Large Instruct 2407 | $0.000 | $0.000 | 66K | 8,192 | — |
| Mixtral 8x22B Instruct V0.1 | $0.000 | $0.000 | 66K | 65,536 | — |
| Mixtral 8x7B Instruct V0.1 | $0.000 | $0.000 | 33K | 32,768 | — |
| Qwen3 Coder:480b Cloud | $0.000 | $0.000 | 262K | 262,144 | — |
Model Details
Codegeex4
Codegeex4 is available via Ollama with a 33K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Deepseek Coder V2 Instruct
Deepseek Coder V2 Instruct is available via Ollama with a 33K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Deepseek Coder V2 Lite Instruct
Deepseek Coder V2 Lite Instruct is available via Ollama with a 33K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Deepseek V3.1:671b Cloud
Deepseek V3.1:671b Cloud is available via Ollama with a 164K context window and up to 163,840 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Gpt Oss:120b Cloud
Gpt Oss:120b Cloud is available via Ollama with a 131K context window and up to 131,072 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Gpt Oss:20b Cloud
Gpt Oss:20b Cloud is available via Ollama with a 131K context window and up to 131,072 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Internlm2 5 20b Chat
Internlm2 5 20b Chat is available via Ollama with a 33K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama2
Llama2 is available via Ollama with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama2:13b
Llama2:13b is available via Ollama with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama2:70b
Llama2:70b is available via Ollama with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama2:7b
Llama2:7b is available via Ollama with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama3
Llama3 is available via Ollama with a 8K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama3.1
Llama3.1 is available via Ollama with a 8K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama3:70b
Llama3:70b is available via Ollama with a 8K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Llama3:8b
Llama3:8b is available via Ollama with a 8K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Mistral 7B Instruct V0.1
Mistral 7B Instruct V0.1 is available via Ollama with a 8K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Mistral 7B Instruct V0.2
Mistral 7B Instruct V0.2 is available via Ollama with a 33K context window and up to 32,768 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Mistral Large Instruct 2407
Mistral Large Instruct 2407 is available via Ollama with a 66K context window and up to 8,192 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Mixtral 8x22B Instruct V0.1
Mixtral 8x22B Instruct V0.1 is available via Ollama with a 66K context window and up to 65,536 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Mixtral 8x7B Instruct V0.1
Mixtral 8x7B Instruct V0.1 is available via Ollama with a 33K context window and up to 32,768 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Qwen3 Coder:480b Cloud
Qwen3 Coder:480b Cloud is available via Ollama with a 262K context window and up to 262,144 output tokens. Pricing: $0.000000/1M input tokens, $0.000000/1M output tokens.
Compare Ollama model pricing
Use our pricing calculator to find the cheapest Ollama model for your workload.