What they do
Submodel provides cloud compute and hosted AI model access, including GPU-backed workloads and OpenAI-compatible inference endpoints.
$10 off the fastest Kimi K3 and GLM 5.2 from Synthetic
Provider details
submodel
Learn more about this provider, then browse the models currently listed under it.
submodelsubmodel
Latest news about submodel
No articles yet. Fetch the latest news to show it here.
About submodel
How they were founded
Public sources reviewed for this seed data describe Submodel as a company created to make cloud and AI compute more accessible, but they do not clearly disclose founders or a founding year.
Quick Info
- Organization
- SubModel
- SDK package
- @ai-sdk/openai-compatible
- Synced at
- Jul 11, 2026
Models served
9 models available through submodel
These model results are sorted newest first so you can quickly see the latest options from this provider.
submodelgpt-oss
Input
Output
submodeldeepseek
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1submodelReleased Aug 23, 202575,000 token context windowIn $0.20 · Out $0.80
Input
Output
submodeldeepseek
DeepSeek V3 0324
deepseek-ai/DeepSeek-V3-0324submodelReleased Aug 23, 202575,000 token context windowIn $0.20 · Out $0.80
Input
Output
submodeldeepseek-thinking
DeepSeek R1 0528
deepseek-ai/DeepSeek-R1-0528submodelReleased Aug 23, 202575,000 token context windowIn $0.50 · Out $2.15
Input
Output
submodelqwen
Qwen3 Coder 480B A35B Instruct
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8submodelReleased Aug 23, 2025262,144 token context windowIn $0.20 · Out $0.80
Input
Output
submodelqwen
Qwen3 235B A22B Thinking 2507
Qwen/Qwen3-235B-A22B-Thinking-2507submodelReleased Aug 23, 2025262,144 token context windowIn $0.20 · Out $0.60
Input
Output
submodelqwen
Qwen3 235B A22B Instruct 2507
Qwen/Qwen3-235B-A22B-Instruct-2507submodelReleased Aug 23, 2025262,144 token context windowIn $0.20 · Out $0.30
Input
Output
submodelglm
Input
Output
submodelglm-air
Input
Output