Ollama Cloud
info Notes
Free tier with usage limits. 16 cloud model families from the Ollama library. OpenAI SDK-compatible via https://ollama.com/v1. []
key How to get API key
General steps — follow the official Ollama Cloud page for exact details.
- Open the Ollama Cloud API key page ↗
- Create a new account, or sign in if you already have one.
- Generate an API key from the dashboard or settings.
layers Available models 29
| Model | Capabilities | Context | Output | Rate limit |
|---|---|---|---|---|
deepseek-v4-pro
deepseek-v4-pro |
description
| 1M | — | Session/weekly limits (unpublished) |
deepseek-v4-flash
deepseek-v4-flash |
description
| 1M | — | Session/weekly limits (unpublished) |
minimax-m3
minimax-m3 |
description
| 512K | — | Session/weekly limits (unpublished) |
kimi-k3
kimi-k3 |
description
| 1M | — | Session/weekly limits (unpublished) |
`gpt-oss:120b`
`gpt-oss:120b` |
description
| 128K | — | Session/weekly limits (unpublished) |
`gpt-oss:20b`
`gpt-oss:20b` |
description
| 131K | — | Session/weekly limits (unpublished) |
nemotron-3-ultra
nemotron-3-ultra |
description
| 262K | — | Session/weekly limits (unpublished) |
`mistral-large-3:675b`
`mistral-large-3:675b` |
description
| 256K | — | Session/weekly limits (unpublished) |
`qwen3.5:397b`
`qwen3.5:397b` |
description
| 256K | — | Session/weekly limits (unpublished) |
+ 7 more cloud models
+-7-more-cloud-models |
description
| Varies | — | Session/weekly limits (unpublished) |
GPT-OSS 120B
gpt-oss-120b |
description
| 1M | — | Monthly starter credits |
GLM 5.2
glm-5.2 |
description
| 1M | — | Monthly starter credits |
Kimi K2.6
kimi-k2.6 |
description
| 1M | — | Monthly starter credits |
Kimi K3
kimi-k3 |
description
| 1M | — | Monthly starter credits |
DeepSeek V4 Pro 0813
deepseek-v4-pro-0813 |
description
| 1M | — | Monthly starter credits |
MiniMax M3
minimax-m3 |
description
| 1M | — | Monthly starter credits |
GLM 5.1
glm-5.1 |
description
| 1M | — | Monthly starter credits |
GLM 5.3
glm-5.3 |
description
| 1M | — | Monthly starter credits |
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731 |
description
| 1M | — | Monthly starter credits |
GPT-OSS 20B
gpt-oss-20b |
description
| 1M | — | Monthly starter credits |
MiniMax M2.7
minimax-m2.7 |
description
| 1M | — | Monthly starter credits |
Mistral Large 3 675B
mistral-large-3-675b |
description
| 1M | — | Monthly starter credits |
Nemotron 3 Super
nemotron-3-super |
description
| 1M | — | Monthly starter credits |
Nemotron 3 Nano 30B
nemotron-3-nano-30b |
description
| 1M | — | Monthly starter credits |
Gemma 4 31B
gemma-4-31b |
description
| 1M | — | Monthly starter credits |
Qwen 3.5 397B
qwen-3.5-397b |
description
| 1M | — | Monthly starter credits |
Nemotron 3 Ultra
nemotron-3-ultra |
description
| 1M | — | Monthly starter credits |
GLM 5.3 Flash
glm-5.3-flash |
description
| 1M | — | Monthly starter credits |
Kimi K2.7 Code
kimi-k2.7-code |
description
| 1M | — | Monthly starter credits |
help Frequently Asked Questions
Ollama Cloud offers 29 free models.
The largest context window is 1,000,000 tokens.
The free tier is limited to Monthly starter credits.