How much does gpt-oss-20b cost?

gpt-oss-20b costs $0.018/M input tokens and $0.09/M output tokens, with separate rates for Cache Read at $0.009/M tokens.

What is the context length of gpt-oss-20b?

gpt-oss-20b has a 131,072 token context window. It supports up to 131,072 completion tokens.

Does gpt-oss-20b support tool calling and structured outputs?

Yes. gpt-oss-20b accepts tools and tool_choice for function calling on 9 of the 10 providers serving it, and requests that send tools are routed to those providers. It also supports structured outputs via a JSON schema in response_format.

Which providers serve gpt-oss-20b?

gpt-oss-20b is served by 10 providers on OpenRouter: Darkbloom, AkashML, Prime Intellect, DekaLLM, CoreWeave, DeepInfra, Parasail, SiliconFlow and 2 more. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was gpt-oss-20b released?

gpt-oss-20b was released on August 5, 2025. Its knowledge cutoff is June 30, 2024.

OpenAI: gpt-oss-20b (nitro)

openai/gpt-oss-20b:nitro

Model weights

Compare

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 lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Modalities

In / out price

$0.018 / $0.09per 1M

Context

131K

Released

Aug 5, 2025

Knowledge cutoff

Jun 2024

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

Input /M	Output /M	Cache read /M	Latency	Throughput	Uptime
$0.07	$0.15	--	0.34s	414 tok/s	100.00%
$0.075	$0.30	$0.0375	0.29s	395 tok/s	99.97%
$0.03	$0.13	$0.03	0.11s	202 tok/s	100.00%
$0.02	$0.03	$0.018	0.60s	127 tok/s	99.88%
$0.07	$0.15	--	0.94s	106 tok/s	100.00%
$0.03	$0.14	--	0.29s	96 tok/s	99.76%
$0.03	$0.15	$0.02	0.67s	87 tok/s	98.22%
$0.018	$0.09	$0.009	0.61s	83 tok/s	99.89%
$0.029	$0.14	$0.029	0.59s	79 tok/s	98.09%
$0.018	$0.09	$0.009	0.59s	75 tok/s	99.57%
$0.04	$0.18	--	1.01s	65 tok/s	95.44%

Input $0.07Output $0.15
414 tok/s100.00% uptime
Input $0.075Output $0.30
395 tok/s99.97% uptime
Input $0.03Output $0.13
202 tok/s100.00% uptime
Input $0.02Output $0.03
127 tok/s99.88% uptime
Input $0.07Output $0.15
106 tok/s100.00% uptime
Input $0.03Output $0.14
96 tok/s99.76% uptime
Input $0.03Output $0.15
87 tok/s98.22% uptime
Input $0.018Output $0.09
83 tok/s99.89% uptime
Input $0.029Output $0.14
79 tok/s98.09% uptime
Input $0.018Output $0.09
75 tok/s99.57% uptime
Input $0.04Output $0.18
65 tok/s95.44% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.04165/M tokens

Output

$0.1765/M tokens

gpt-oss-20b — Price history

Price history

No effective price data for this selection

$0.0152	$0.0896	29.1%	4.0%
$0.0159	$0.0887	20.2%	7.3%
$0.0208	$0.0326	41.8%	4.4%
$0.0245	$0.1494	53.7%	2.9%
$0.0289	$0.1394	42.7%	0.5%
$0.0298	$0.1391	0.0%	13.5%
$0.0299	$0.1294	19.7%	26.5%
$0.0397	$0.1793	0.0%	0.3%
$0.0613	$0.2992	36.1%	29.2%
$0.0699	$0.1492	0.0%	10.4%
$0.0699	$0.1492	0.0%	0.9%

Effective in $0.0152Effective out $0.0896
Token share
4.0%
Effective in $0.0159Effective out $0.0887
Token share
7.3%
Effective in $0.0208Effective out $0.0326
Token share
4.4%
Effective in $0.0245Effective out $0.1494
Token share
2.9%
Effective in $0.0289Effective out $0.1394
Token share
0.5%
Effective in $0.0298Effective out $0.1391
Token share
13.5%
Effective in $0.0299Effective out $0.1294
Token share
26.5%
Effective in $0.0397Effective out $0.1793
Token share
0.3%
Effective in $0.0613Effective out $0.2992
Token share
29.2%
Effective in $0.0699Effective out $0.1492
Token share
10.4%
Effective in $0.0699Effective out $0.1492
Token share
0.9%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

414tok/s

P50, best across providers

Latency

0.11s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchDekaLLM68.3%--SiliconFlow62.8%--auto-routing67.3%51.6%Darkbloom65.1%50.2%Google57.2%--

+6 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

100.00%

Availability (3d)

97.48%

Availability over the last 3 days

Last 72 hours

Availability 97.48%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

97.58%

Without Routing

95.13%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for OpenAI: gpt-oss-20b (Artificial Analysis, Design Arena and Vals AI)
Source	Benchmark	Score
Artificial Analysis	gpt-oss-20b (Low) GPQA Diamond	61.1%
Artificial Analysis	gpt-oss-20b (Low) HLE	5.3%
Artificial Analysis	gpt-oss-20b (Low) IFBench	57.8%
Artificial Analysis	gpt-oss-20b (Low) τ²-Bench Telecom	50.3%
Artificial Analysis	gpt-oss-20b (Low) AA-LCR	31.0%
Artificial Analysis	gpt-oss-20b (Low) CritPt	0.0%
Artificial Analysis	gpt-oss-20b (Low) LiveCodeBench	65.2%
Artificial Analysis	gpt-oss-20b (Low) Terminal-Bench Hard	4.5%
Artificial Analysis	gpt-oss-20b (Low) MMLU-Pro	71.8%
Artificial Analysis	gpt-oss-20b (Low) AIME 2025	62.3%
Artificial Analysis	gpt-oss-20b (High) Coding Index	20.7
Artificial Analysis	gpt-oss-20b (High) Agentic Index	1.2
Artificial Analysis	gpt-oss-20b (High) GPQA Diamond	68.8%
Artificial Analysis	gpt-oss-20b (High) HLE	11.0%
Artificial Analysis	gpt-oss-20b (High) IFBench	65.1%
Artificial Analysis	gpt-oss-20b (High) τ²-Bench Telecom	60.2%
Artificial Analysis	gpt-oss-20b (High) AA-LCR	34.7%
Artificial Analysis	gpt-oss-20b (High) τ-Bench Banking	7.0%
Artificial Analysis	gpt-oss-20b (High) GDPval-AA	0.0%
Artificial Analysis	gpt-oss-20b (High) CritPt	1.4%
Artificial Analysis	gpt-oss-20b (High) LiveCodeBench	77.7%
Artificial Analysis	gpt-oss-20b (High) SciCode	38.9%
Artificial Analysis	gpt-oss-20b (High) Terminal-Bench Hard	10.6%
Artificial Analysis	gpt-oss-20b (High) Terminal-Bench 4.0	0.0%
Artificial Analysis	gpt-oss-20b (High) Terminal-Bench 2.1	13.9%
Artificial Analysis	gpt-oss-20b (High) MMLU-Pro	74.8%
Artificial Analysis	gpt-oss-20b (High) AIME 2025	89.3%
Design Arena	GPT OSS 20B Models Arena Data Visualization Elo	933
Design Arena	GPT OSS 20B Models Arena Website Elo	844
Vals AI	GPT OSS 20B AIME	86.0%
Vals AI	GPT OSS 20B CaseLaw v2	43.8%
Vals AI	GPT OSS 20B CorpFin v2	53.1%
Vals AI	GPT OSS 20B GPQA Diamond	68.9%
Vals AI	GPT OSS 20B LiveCodeBench	80.4%
Vals AI	GPT OSS 20B LegalBench	70.8%
Vals AI	GPT OSS 20B MATH 500	94.2%
Vals AI	GPT OSS 20B MedQA	82.9%
Vals AI	GPT OSS 20B MGSM	89.0%
Vals AI	GPT OSS 20B MMLU Pro	71.6%
Vals AI	GPT OSS 20B TaxEval v2	63.7%

Available through EU in-region routing

OpenAI: gpt-oss-20b (nitro) is available through EU in-region routing. Requests sent to eu.openrouter.ai are decrypted in the EU and routed only to shared provider endpoints in Europe (the EU/EEA, the UK, and Switzerland).

Providers in Europe

Amazon Bedrock

Prices in Europe

Amazon Bedrock: $0.07/M tokens input, $0.15/M tokens output

Base URL

https://eu.openrouter.ai/api/v1

Plan

Requires Business or Enterprise. Self-serve on Business: no contract, no monthly minimum. OpenRouter Business for EU in-region routing

Fails closed: if no shared provider endpoint in Europe is available, the request errors instead of leaving the region. Requests served by your own BYOK key go to your deployment’s region, which you control. In-region routing docs

More models from OpenAI

GPT Image 2.6 Sunburst

GPT Image 2.6 Sunburst is OpenAI's image generation and editing model optimized for detail: dense compositions, text-heavy layouts, and edits that keep details consistent from one edit to the next at medium or high quality, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Flare instead when speed matters more than fine detail.

Image$8 / $30

GPT Image 2.6 Flare

GPT Image 2.6 Flare is OpenAI's image generation and editing model optimized for speed: fast iteration and interactive text-to-image and image-to-image workflows, generating about 50% faster than GPT Image 2.5. It takes text and image inputs and produces images, with quality tiers from low to max, transparent backgrounds, and custom sizes in multiples of 16 pixels at aspect ratios from 1:3 to 3:1. GPT Image 2.6 introduces a complexity setting for how much the model plans before rendering, markup-guided edits, animated GIF output, and SVG output. Choose Sunburst instead when detail and edit-to-edit consistency matter more than latency.

Image$8 / $30

GPT-6.1 Terra Pro

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Terra and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Terra instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Terra Pro (batch)

GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.50 / $2.50

GPT-6.1 Terra

GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots and on-screen content, and is efficient enough for high-volume workloads.

Text1.1M context$1 / $5

GPT-6.1 Terra (batch)

Text1.1M context$0.50 / $2.50

GPT-6 Luna Decisions

GPT-6 Luna Decisions is GPT-6 Luna served through OpenAI's Decisions API. Instead of generating text, it reads the content passed as state (text, JSON, or images) and returns typed, probabilistic answers to named questions in a single request: the probability of yes for a yes/no question (noul), a probability for every option plus the most likely one (choice), or a probability for every level of an ordered rubric plus the expected score (score).

It is built for classification, routing, moderation, and rubric grading where application code thresholds the returned numbers rather than parsing a chat reply. A request can carry up to 200 questions about the same content.

Decisions$0.10 / $0

GPT-6.1 Sol Pro

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6.1 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6.1 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6.1 Sol Pro (batch)

GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

Text1.1M context$2 / $10

GPT-6.1 Sol (batch)

Text1.1M context$1 / $5

GPT-6 Luna Pro

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Luna and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Luna instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.10 / $0.50

GPT-6 Luna Pro (batch)

GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$0.05 / $0.25

GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

Text1.1M context$0.10 / $0.50

GPT-6 Luna (batch)

Text1.1M context$0.05 / $0.25

GPT-6 Sol Pro

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Cost note: pro mode spends far more reasoning tokens per request, so a typical request costs several times more than the same request on GPT-6 Sol and takes much longer to complete. It is intended for hard, high-stakes problems where the extra accuracy justifies the cost. For everyday coding, agentic, and chat workloads, use GPT-6 Sol instead.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$2 / $10

GPT-6 Sol Pro (batch)

GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.

Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Text1.1M context$1 / $5

GPT-6 Sol

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

Text1.1M context$2 / $10

GPT-6 Sol (batch)

Text1.1M context$1 / $5

GPT Astra Latest

This model always redirects to the latest model in the GPT Astra family.

Text1.1M context

OpenAI: gpt-oss-20b (nitro)

Providers