aiticker

OpenAI · Released Aug 5, 2025

gpt-oss-20b

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, optimized for...

ReasoningOpen weights
Compare in showdown → OpenRouter ↗ All OpenAI models
Released
Aug 5 2025
Context window
131K 33K out
Input / 1M tokens
$0.018 from Free
Output / 1M tokens
$0.09 from Free

Where to run it

43 providers compared

Free to try on Nvidia — free endpoints are often limited-time and rate-limited. Cheapest: Darkbloom, Kilo Gateway at $0.018 / $0.09 per 1M input / output tokens — 85% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
Nvidiafree · may be limited-time Free Free —131K33K— Free
DarkbloomFP8 $0.018 $0.09 $0.009131K33K100%24h Cheapest
Kilo Gateway $0.018 $0.09 $0.009131K33K— Cheapest
AkashMLFP4 $0.02 $0.10 —131K118K100%24h +11%
NanoGPT $0.02 $0.10 —131K16K— +11%
CoreWeaveFP4 $0.03 $0.13 $0.03131K118K100%24h +53%
DekaLLMBF16 $0.029 $0.14 $0.029131K118K100%24h +58%
DeepInfraBF16 $0.03 $0.14 —131K118K99.2%24h +60%
Vercel AI Gateway $0.03 $0.14 —131K8K— +60%
ParasailFP4 $0.03 $0.15 $0.02131K118K99.9%24h +67%
Kenari $0.036 $0.15 $0.004131K33K— +82%
Merge Gatewayno tool calling $0.04 $0.15 $0.02128K32K— +88%
SiliconFlowFP8 · no tool calling $0.04 $0.18 —131K8K92.5%24h +108%
Cortecs $0.045 $0.17 —131K131K— +110%
DevPass (LLM Gateway) $0.04 $0.19 $0.01131K33K— +115%
Clarifai $0.045 $0.18 —131K16K— +119%
OVHcloud AI Endpoints $0.05 $0.18 —131K131K— +129%
Helicone $0.05 $0.20 —131K131K— +143%
IO.NET $0.055 $0.19 $0.02864K4K— +149%
Amazon Bedrockeu-west-1 $0.07 $0.15 —131K118K100%24h +150%
Amazon Bedrock $0.07 $0.15 —131K118K100%24h +150%
FrogBot $0.07 $0.20 —131K33K— +185%
Googleus-central1 · no tool calling $0.07 $0.25 —131K33K56.9%24h +219%
FastRouter $0.07 $0.25 $0.007131K33K— +219%
Databricks $0.07 $0.30 —131K25K— +254%
Pioneer $0.07 $0.30 $0.035131K8K— +254%
Prime Inference $0.07 $0.30 —131K33K— +254%
Neon $0.07 $0.30 —131K25K— +254%
Ollama Cloud $0.07 $0.30 $0.035131K33K— +254%
OCI Generative AI $0.07 $0.30 —128K16K— +254%
Groq $0.075 $0.30 $0.038131K66K97%24h +265%
Tempr Gateway $0.075 $0.30 $0.038131K66K— +265%
Impossibl $0.075 $0.30 $0.038131K33K— +265%
Eden AI $0.075 $0.30 $0.038131K33K— +265%
DigitalOcean $0.05 $0.45 $0.01128K4K— +317%
AI/ML API $0.10 $0.41 $0.052131K118K— +401%
LLM Gateway $0.10 $0.50 —131K33K— +456%
Hugging Face $0.10 $0.50 —131K33K— +456%
Regolo AI $0.11 $0.47 —128K16K— +460%
LowRouter $0.11 $0.47 —131K33K— +465%
STACKIT $0.18 $0.29 —131K8K— +476%
Opper $0.12 $0.49 —128K8K— +481%
Cloudflare Workers AI $0.20 $0.30 —128K16K— +525%
Thinking Machines $0.18 $0.45 $0.03633K33K— +588%

Value

Price vs. performance

1 model scores higher for the same price or lesson GPQA Diamond, e.g. GLM 5.3 Flash.
23.2%47.6%72.0%96.4% $0.001$0.01$0.10$1.00$10.00$100.00 DeepSeek V4.1 Flash 1017 (DeepSeek) — 93.2% · $0.15/1M in Gemini 4 Argon (Google) — 96.4% · $2.00/1M in Claude Haiku 5.5 (Anthropic) — 89.6% · $0.10/1M in Mistral Large 4 (Mistral) — 88.1% · $1.36/1M in Claude Sonnet 5.5 (Anthropic) — 95.6% · $2.00/1M in Claude Opus 5.5 (Anthropic) — 90.6% · $4.00/1M in Grok 4.7 (xAI) — 92.7% · $2.00/1M in DeepSeek V4.1 Flash (DeepSeek) — 93.2% · $0.30/1M in Qwen3.8 Max (0902) (Qwen) — 92.7% · $2.00/1M in Gemini 3.8 Flash (Google) — 95.4% · $0.82/1M in GLM 5.3 Flash (Z.ai) — 90.1% · $0.005/1M in GLM 5.3 (Z.ai) — 90.9% · $0.079/1M in Gemini 3.7 Flash (Google) — 94.8% · $0.75/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 91.7% · $0.66/1M in Grok 4.6 (xAI) — 94.0% · $2.00/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 91.0% · $0.44/1M in Qwen3.7 Flash (Qwen) — 82.3% · $0.03/1M in Claude Opus 5 (Anthropic) — 93.9% · $5.00/1M in Gemini 3.6 Flash (Google) — 94.1% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 83.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 93.1% · $0.24/1M in Grok 4.5 (xAI) — 93.4% · $2.00/1M in Claude Sonnet 5 (Anthropic) — 90.5% · $2.00/1M in GLM 5.2 (Z.ai) — 91.9% · $0.034/1M in Kimi K2.7 Code (Moonshot AI) — 87.9% · $0.67/1M in Claude Fable 5 (Anthropic) — 85.9% · $10.00/1M in Qwen3.7 Plus (Qwen) — 87.9% · $0.32/1M in MiniMax M3 (MiniMax) — 90.9% · $0.30/1M in Claude Opus 4.8 (Anthropic) — 91.0% · $5.00/1M in Qwen3.7 Max (Qwen) — 90.9% · $1.48/1M in Gemini 3.5 Flash (Google) — 92.8% · $1.50/1M in Gemini 3.1 Flash Lite (Google) — 81.8% · $0.25/1M in Grok 4.3 (xAI) — 88.8% · $1.25/1M in Qwen3.5 Plus 2026-04-20 (Qwen) — 84.9% · $0.30/1M in Qwen3.6 Flash (Qwen) — 83.3% · $0.19/1M in Qwen3.6 35B A3B (Qwen) — 84.9% · $0.10/1M in Qwen3.6 27B (Qwen) — 85.9% · $0.25/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 91.7% · $0.45/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 91.0% · $0.091/1M in Kimi K2.6 (Moonshot AI) — 90.8% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 90.1% · $5.00/1M in GLM 5.1 (Z.ai) — 89.9% · $1.40/1M in Gemma 4 26B A4B (Google) — 73.2% · $0.09/1M in Gemma 4 31B (Google) — 75.8% · $0.20/1M in Qwen3.6 Plus (Qwen) — 88.4% · $0.33/1M in Mistral Small 4 (Mistral) — 47.5% · $0.15/1M in Qwen3.5-9B (Qwen) — 79.0% · $0.08/1M in Gemini 3.1 Flash Lite Preview (Google) — 81.8% · $0.25/1M in Qwen3.5-35B-A3B (Qwen) — 83.5% · $0.14/1M in Gemini 3.1 Pro Preview (Google) — 94.4% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 87.4% · $3.00/1M in Qwen3.5 397B A17B (Qwen) — 86.4% · $0.50/1M in GLM 5 (Z.ai) — 87.8% · $1.00/1M in Claude Opus 4.6 (Anthropic) — 90.5% · $5.00/1M in GLM 4.7 Flash (Z.ai) — 60.5% · $0.061/1M in GLM 4.7 (Z.ai) — 83.3% · $0.54/1M in Gemini 3 Flash Preview (Google) — 89.4% · $0.50/1M in Ministral 3 8B 2512 (Mistral) — 27.2% · $0.15/1M in Ministral 3 3B 2512 (Mistral) — 25.3% · $0.10/1M in Mistral Large 3 2512 (Mistral) — 51.3% · $0.50/1M in Claude Opus 4.5 (Anthropic) — 86.1% · $5.00/1M in Claude Haiku 4.5 (Anthropic) — 71.2% · $1.00/1M in Claude Sonnet 4.5 (Anthropic) — 82.3% · $3.00/1M in Claude Opus 4.1 (Anthropic) — 77.3% · $15.00/1M in Qwen3 30B A3B Instruct 2507 (Qwen) — 55.6% · $0.09/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 80.0% · $0.45/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 70.7% · $0.09/1M in Gemini 2.5 Pro (Google) — 85.3% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 85.3% · $1.25/1M in R1 0528 (DeepSeek) — 76.3% · $0.50/1M in Qwen3 30B A3B (Qwen) — 61.7% · $0.12/1M in Qwen3 14B (Qwen) — 63.8% · $0.12/1M in Qwen3 32B (Qwen) — 65.7% · $0.08/1M in Gemma 3 4B (Google) — 23.2% · $0.04/1M in Gemma 3 12B (Google) — 39.5% · $0.05/1M in Gemma 3 27B (Google) — 47.7% · $0.08/1M in Qwen-Plus (Qwen) — 48.1% · $0.26/1M in Phi 4 (Microsoft) — 56.1% · $0.07/1M in DeepSeek V3 (DeepSeek) — 71.2% · $0.26/1M in Llama 3.3 70B Instruct (Meta) — 47.4% · $0.10/1M in Mistral Large 2407 (Mistral) — 51.3% · $2.00/1M in Llama 3.2 1B Instruct (Meta) — 23.9% · $0.027/1M in Llama 3.1 70B Instruct (Meta) — 44.2% · $0.40/1M in Llama 3.1 8B Instruct (Meta) — 27.0% · $0.05/1M in Gemma 2 27B (Google) — 36.5% · $0.65/1M in Mistral Large (Mistral) — 51.3% · $2.00/1M in GPT-6.1 Sol (OpenAI) — 95.4% · $2.00/1M in GPT-6 Luna (OpenAI) — 90.5% · $0.10/1M in GPT-6 Sol (OpenAI) — 94.3% · $2.00/1M in GPT-6 Astra (OpenAI) — 95.8% · $10.00/1M in GPT-5.6 Luna (OpenAI) — 91.6% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 93.3% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 93.5% · $4.00/1M in GPT-5.5 (OpenAI) — 90.7% · $5.00/1M in GPT-5.4 Nano (OpenAI) — 78.5% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 86.9% · $0.75/1M in GPT-5.4 Pro (OpenAI) — 94.6% · $30.00/1M in GPT-5.4 (OpenAI) — 93.3% · $2.50/1M in GPT-5.2 (OpenAI) — 91.4% · $1.75/1M in GPT-5.1 (OpenAI) — 87.6% · $1.25/1M in GPT-5 (OpenAI) — 86.2% · $1.25/1M in GPT-5 Mini (OpenAI) — 75.0% · $0.25/1M in GPT-5 Nano (OpenAI) — 69.4% · $0.05/1M in gpt-oss-120b (OpenAI) — 75.8% · $0.15/1M in o3 (OpenAI) — 81.8% · $2.00/1M in o4 Mini (OpenAI) — 79.6% · $1.10/1M in GPT-4.1 (OpenAI) — 66.9% · $2.00/1M in GPT-4.1 Mini (OpenAI) — 65.8% · $0.40/1M in GPT-4.1 Nano (OpenAI) — 48.9% · $0.10/1M in o3 Mini (OpenAI) — 77.0% · $1.10/1M in o1 (OpenAI) — 76.8% · $15.00/1M in GPT-4o (2024-11-20) (OpenAI) — 49.2% · $2.50/1M in GPT-4o (2024-08-06) (OpenAI) — 49.2% · $2.50/1M in GPT-4o-mini (OpenAI) — 37.7% · $0.15/1M in GPT-4o-mini (2024-07-18) (OpenAI) — 37.7% · $0.15/1M in GPT-4o (OpenAI) — 49.2% · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 49.2% · $5.00/1M in GPT-4 Turbo (OpenAI) — 46.6% · $10.00/1M in GPT-3.5 Turbo (older v0613) (OpenAI) — 28.0% · $1.00/1M in GPT-3.5 Turbo (OpenAI) — 28.0% · $0.50/1M in GPT-4 (OpenAI) — 35.7% · $30.00/1M in gpt-oss-20b (OpenAI) — 60.8% · $0.018/1M in gpt-oss-20b

gpt-oss-20b Other OpenAI Other labs Value frontier · GPQA Diamond vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

6 benchmark scores

BenchmarkScoreRankLeader
Terminal-BenchSoftware engineering · Tasks completed with the programs in a real terminal (best agent) 3.4% #40of 40 GPT-5.584.7%
SciCodeSoftware engineering · Research-coding problems from the natural sciences 38.9% #79of 102 Claude Opus 5.566.9%
GPQA DiamondReasoning & knowledge · PhD-level biology, chemistry and physics questions 60.8% #93of 122 Gemini 4 Argon96.4%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 1.4% #73of 111 GPT-5.6 Sol32.3%
LMCAReasoning & knowledge · Judge the quality of conceptual arguments like experts 14.5% #111of 123 Claude Sonnet 5.568.3%
OTIS Mock AIMEMaths · Competition-style problems harder than MATH Level 5 65.3% #88of 120 Gemini 4 Argon100.0%

Specs

Details

Model ID
openai/gpt-oss-20b
Developer
OpenAI
Release date
Aug 5, 2025 ·
Context window
131,072 tokens
Max output
32,768 tokens
API price
$0.018 / $0.09 per 1M input / output tokens
Providers
43
Input types
text
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.