gpt-oss-20b API Benchmarks, Pricing & Provider Data
Compare gpt-oss-20b with another model
Choose a model to open its comparison page.
gpt-oss-20b benchmark, API pricing, and provider data cover undefined API provider} other undefined API providers}}, with prices starting at $0.0005/M. gpt-oss-20b free API options are available from undefined provider} other undefined providers}}.
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimiz...
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 6 / 8
- Methodology
- V3.0
#1Math53Provisional1/4 Measured dimensions
#2Instruction following51Provisional1/4 Measured dimensions
#3Coding47.9Estimated2/4 Measured dimensions
#4Reasoning44RatedGlobal rank #593/4 Measured dimensions
#5Agents38Estimated3/4 Measured dimensions
#6Knowledge35.6Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Total parameters
- 20B
- Released
- Aug 2025
- Knowledge cutoff
- 2024-06-30
- Tokenizer
- GPT
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Sep 13, 2026Speed & latency
undefined metric} other undefined metrics}}
Output speed268.3 tok/s#9 / 80Time to first token0.52 s#10 / 80
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.070/M#7 / 186Output price$0.200/M#3 / 186
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Score3880% interval28.7–47.23/4 Measured dimensionsAA Agentic Index3.1#63 / 70APEX-Agents-AA0.7#23 / 23
Agents
V3.0undefined metric} other undefined metrics}} · Estimated
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Score47.980% interval36.6–59.12/4 Measured dimensionsLiveCodeBench65.2%#37 / 115SciCode38.9%#65 / 89
Coding
V3.0undefined metric} other undefined metrics}} · Estimated
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Score44#5980% interval35.3–52.73/4 Measured dimensionsMMLU-Pro71.8%#97 / 129GPQA61.1%#165 / 218
Reasoning
V3.0undefined metric} other undefined metrics}} · Rated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score35.680% interval19.6–51.61/4 Measured dimensionsArtificial Analysis Intelligence Index15.2#97 / 117AA-GPQA Diamond68.8#91 / 113
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Score5380% interval36.8–69.11/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · Provisional
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website875.0#76 / 78
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
Score5180% interval35.0–67.01/4 Measured dimensionsAA-IFBench65.1#44 / 84
Instruction following
V3.0undefined metric} other undefined metrics}} · Provisional
OpenRouter endpoints
14 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Amazon Bedrock amazon-bedrock/eu-west-1 | $0.070/M | $0.150/M | 100% | — | — | undefined tokens / undefined tokens |
CoreWeave coreweave/fp4 | $0.030/M | $0.130/M | 100.0% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/bf16 | $0.030/M | $0.140/M | 100.0% | — | — | undefined tokens / undefined tokens |
Novita novita/fp4 | $0.040/M | $0.150/M | 99.9% | — | — | undefined tokens / undefined tokens |
Parasail parasail/fp4 | $0.030/M | $0.150/M | 99.9% | — | — | undefined tokens / undefined tokens |
Amazon Bedrock amazon-bedrock | $0.070/M | $0.150/M | 99.9% | — | — | undefined tokens / undefined tokens |
Phala phala | $0.040/M | $0.150/M | 99.9% | — | — | undefined tokens / undefined tokens |
Google google-vertex/us-central1 | $0.070/M | $0.250/M | 99.8% | — | — | undefined tokens / undefined tokens |
Groq groq | $0.075/M | $0.300/M | 99.8% | — | — | undefined tokens / undefined tokens |
Darkbloom darkbloom/fp8 | $0.020/M | $0.100/M | 99.7% | — | — | undefined tokens / undefined tokens |
DekaLLM dekallm/bf16 | $0.029/M | $0.140/M | 99.6% | — | — | undefined tokens / undefined tokens |
AkashML akashml/fp4 | $0.020/M | $0.100/M | 99.3% | — | — | undefined tokens / undefined tokens |
Together together | $0.050/M | $0.200/M | 99.0% | — | — | undefined tokens / undefined tokens |
SiliconFlow siliconflow/fp8 | $0.040/M | $0.180/M | 98.7% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare gpt-oss-20b API pricing across 12 providers. Prices range from $0.0005/M to $77.05/M. 云AI offers the lowest rate at $0.0005/M. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | gpt-oss-20b | mix | -99%$0.0005/M | -99%$0.0026/M | — | — | — | |
L1 100% | gpt-oss-20b | deepseek | -96%$0.0027/M | -95%$0.0099/M | — | — | — | |
L1 100% | gpt-oss-20b | default | -82%$0.013/M Cache read$0.013/MCache write$0/MCache write 1h$0/M | -72%$0.055/M | — | — | — | |
兔子API Free | L1 99% | gpt-oss-20b-free | 原价分组 | Free | Free | — | — | — |
L1 100% | openai/gpt-oss-20b | default | $10.27/M | $10.27/M | — | — | — | |
Moyanjdc API Free | L1 99% | gpt-oss:20b | default | Free | Free | — | — | — |
L1 39% | accounts/fireworks/models/gpt-oss-20b | 测试专用 | $9.59/M Cache read$4.79/M | $41.10/M | — | — | — | |
L1 100% | gpt-oss-20b | default | $0.010/request | - | — | — | — | |
L1 100% | laohuang/openai/gpt-oss-20b | default | $0.020/request | - | — | — | — |
Alternatives & Similar Models
GPT-5.4
gpt-5-4
OpenAI GPT-5.4 extends the GPT-5 family with stronger instruction following, deeper tool use, and improved performance on coding, math, and long-document analysis.
GPT-5.3 Codex
gpt-5-3-codex
OpenAI GPT-5.3 Codex is a code-specialized variant in the GPT-5 series, optimized for code generation, debugging, and software development tasks.
GPT-5.2
gpt-5-2
OpenAI GPT-5.2 is a GPT-5 series model emphasizing advanced reasoning, multimodal understanding, and high-quality outputs for complex enterprise workloads.
GPT-5.4 Mini
gpt-5-4-mini
OpenAI GPT-5.4 Mini is a compact language model in the GPT-5 series, optimized for quick responses and high throughput.
Claude Opus 4.6
claude-opus-4-6
Anthropic Claude Opus 4.6 is the most capable Claude Opus tier, optimized for complex analysis, long-horizon coding, and high-stakes enterprise reasoning workloads.
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
Frequently Asked Questions
- What benchmark data does gpt-oss-20b include?
- LMSpeed shows gpt-oss-20b benchmark context, API price, output speed, first-token latency, and provider data across 14 providers when those signals are available.
- What is the gpt-oss-20b API price?
- gpt-oss-20b has pricing from undefined provider} other undefined providers}}, ranging from $0.0005/M to $77.05/M. 云AI has the lowest listed price.
- What does the gpt-oss-20b API pricing table include?
- The gpt-oss-20b API pricing table compares 14 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest gpt-oss-20b API pricing?
- 云AI currently has the lowest listed gpt-oss-20b price at $0.0005/M across undefined provider} other undefined providers}}.
- Is gpt-oss-20b API free?
- Yes, gpt-oss-20b free API options are available through 2 providerundefined other undefined} on LMSpeed, including 兔子API, Moyanjdc API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get gpt-oss-20b free API access?
- LMSpeed currently lists 2 free API providerundefined other undefined} for gpt-oss-20b: 兔子API, Moyanjdc API. Check each provider row before using it because free tier limits can change.