GPT OSS 20B
DeprecatedGPT OSS 20B is OpenAI's language model with a 131K context window and up to 131K output tokens, available from 17 providers, starting at $0.0145 / 1M input and $0.07 / 1M output. A 20-billion-parameter open-weights GPT model from OpenAI suited for reasoning and tool-use tasks at a smaller, more efficient scale.
| Benchmarks | |
|---|---|
| Intelligence Index | #315 |
| Coding Index | #153 |
| Math Index | #41 |
| MMLU-Pro | #191 |
| GPQA | #280 |
| HLE | #225 |
| LiveCodeBench | #43 |
| IFBench | #97 |
| Time to First Token | #379 |
| SciCode | #197 |
| AIME 2025 | #41 |
| LCR | #304 |
| TerminalBench Hard | #221 |
| TAU2 | #173 |
| Output TPS | #11 |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search✓
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Flex | Fast | Batch | ||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | Cache Write 5m $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.07 | $0.3 | N/A | N/A | $0.035 | $0.15 | $0.122 | $0.525 | $0.035 | $0.15 | |
| $0.2 | $0.3 | N/A | N/A | — | — | — | — | — | — | |
| $0.0145 | $0.07 | N/A | N/A | — | — | — | — | — | — | |
| $0.07 | $0.3 | $0.07 | $0.07 | — | — | — | — | — | — | |
| $0.03 | $0.14 | N/A | N/A | — | — | — | — | — | — | |
| $0.07 | $0.3 | $0.035 | N/A | — | — | — | — | — | — | |
| $0.07 | $0.25 | $0.007 | N/A | — | — | — | — | $0.035 | $0.125 | |
| $0.075 | $0.3 | $0.0375 | N/A | — | — | — | — | — | — | |
| $0.1 | $0.5 | N/A | N/A | — | — | — | — | — | — | |
| $0.05 | $0.18 | N/A | N/A | — | — | — | — | — | — | |
| $0.04 | $0.15 | N/A | N/A | — | — | — | — | — | — | |
| $0.018 | $0.09 | $0.009 | N/A | — | — | — | — | N/A | N/A | |
| — | — | — | — | — | — | — | — | $0.024 | $0.112 | |
| $0.04 | $0.15 | N/A | N/A | — | — | — | — | — | — | |
| $0.09 | $0.36 | N/A | N/A | — | — | — | — | — | — | |
| $0.07 | $0.28 | N/A | N/A | — | — | — | — | — | — | |
| $0.05 | $0.2 | N/A | N/A | — | — | — | — | — | — | |
| $0.03 | $0.14 | N/A | N/A | — | — | — | — | — | — | |
| $0.03 | $0.13 | N/A | N/A | — | — | — | — | — | — | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host GPT OSS 20B, ranked by cheapest on-demand price. The model needs about 48 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP10s |  Azure | AMD Alveo U250 FPGA (64GB) | 64 GB | $1.65/hr | ||
| Standard_NV32as_v4 | Azure | AMD Radeon Instinct MI25 | 64 GB | $1.86/hr | ||
| g2-standard-24 |  GCP | 2× nvidia-l4 | 48 GB | $1.99/hr | ||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GPT OSS 120B Safeguard | 131K | $0.150 | $0.600 | Available | |
| GPT OSS 20B Safeguard | 131K | $0.070 | $0.200 | Available | |
| GPT OSS 20B | 131K | $0.015 | $0.070 | Current | |
| GPT OSS 120B | 131K | $0.030 | $0.170 | Available |