OpenAI · GPT-OSS
GPT-OSS 120B
Verified by Badgr · ServeGPT-OSS 120B is a 120B chat and text-generation model available through supported Badgr execution routes.
Last validated or meaningfully updated: 2026-10-10
✓ Verified by Badgr · vLLM · Serve
Last verified 2026-10-10
badgr serve openai/gpt-oss-120b --max-cost 5- GPU
- NVIDIA H100 80GB HBM3Reported by the provider, not confirmed inside the container
- Time to verified
- 455s
- Deployment
- dep-541706d9f9
- ✓ vLLM started
- ✓ 1-token /v1/completions request returned HTTP 200
- ✓ final_state = VERIFIED
- ✓ teardown completed
A 120B mixture-of-experts model served on one H100 80GB with Badgr's default 65,536-token context cap. Verification used a 1-token completion; this is a start-up and health proof, not a quality or throughput test.
Raw evidence
final_state=VERIFIED failure_class=None providers_tried=1/1 teardown_confirmed=False spend_usd=0.4216
Run from Badgr's local development environment. Documents that this deployment path works end-to-end for this model.
Availability
✓ Badgr AI API
Available through Badgr
✓ Dedicated endpoint
Available through Badgr
✓ Custom GPU deployment
Available through Badgr
Deployment profile
- Architecture
- GptOssForCausalLM
- Licence
- Apache-2.0
- Minimum VRAM
- ~244GB
- Context
- 128K tokens
Recommended: H200 141GB. VRAM is an estimate and increases with context, cache, concurrency, and runtime overhead.
Model identity
- Updated
- 1 years ago
- HuggingFace revision
- b5c939de8f
Popularity and trust
Downloads (last month)
3.8M
Likes
5.4K
Spaces using this model
100
Files and formats
Weight formats
Safetensors, PyTorch bin
Repository files
37
Chat template
Available
GPU deployment scenarios
Estimated from parameter count and quantisation. This model's one verified real run was reported by the provider as NVIDIA H100 80GB HBM3, which isn't one of the tiers below.
Testing
A100 80GB
Short context, low concurrency
Small production
H100 80GB
8K context, 1-4 concurrent requests
Higher throughput
H200 141GB
32K context, continuous batching
Large production
2× H200 141GB
Tensor parallel, higher concurrency
Estimated — multimodal inputs, long context, and concurrency all increase real VRAM use beyond this estimate.
Also runs well on H100 80GB. Available in United States, Europe.
Serving compatibility
| Runtime | Status | Notes |
|---|---|---|
| vLLM | Verified by Badgr | Confirmed by a real badgr serve run (deployment dep-541706d9f9) |
| Transformers | Declared by source | Basic fallback |
| llama.cpp | Requires GGUF conversion | No GGUF weights found in repo |
| SGLang | Unknown | Not evaluated |
| Ollama | Unknown | Not evaluated |
| Diffusers | Unknown | Not evaluated |
| PyTorch | Unknown | Not evaluated |
| TensorRT-LLM | Unknown | Conversion may be required |
| TGI | Unknown | Not evaluated |
Call this model through Badgr
curl https://aibadgr.com/v1/chat/completions \
-H "Authorization: Bearer $BADGR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"Hello"}]}'Ready-to-run Badgr configurations
Quick test
badgr serve openai/gpt-oss-120b --max-cost 2Validated dedicated endpoint command
badgr serve openai/gpt-oss-120b --gpu H200 --max-cost 10Advanced configuration (defaults to automatic)
- Runtime
- Quantisation
- GPU and GPU count
- Context length
- Maximum concurrency
- Region
- Maximum hourly spend
- Persistent or capped runtime
Estimated pricing
Provider estimate: cold start
2–5 min
Provider estimate: endpoint cost
$1.90 – $1.90/hr
Idle cost
$0 when stopped
Per-token throughput cost is not shown here: Badgr has not benchmarked this model yet, and this page does not display figures it cannot back with real data.
Recommended Badgr routes
H100 80GB · Europe
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
H100 80GB · Europe
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
H100 80GB · Europe
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
H100 80GB · Europe
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
H100 80GB · Europe
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
H100 80GB · Asia Pacific
Estimatedstarting from $1.90/hr
Badgr estimated starting price
Best for
LoRA Training, vLLM Endpoint, Qwen 2.5 32B Instruct
Startup: 2–5 min
Reliability: High
Last checked: Live marketplace price not available yet
Known limitations
- Memory use increases with context length and concurrency.