Enterprise DNAEnterprise DNA
OpenAI logo

Models · Best cheap

GPT OSS 20B

by Accounts

Open-weight GPT model for self-hosted reasoning and instruction-following workloads.

Visit Accounts ↗

Our verdict

Not reviewed yet

We have not reviewed GPT OSS 20B yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About GPT OSS 20B

Open-weight GPT model for self-hosted reasoning and instruction-following workloads.

Notes

GPT OSS 20B is listed in the EDNA Models directory, sourced from models.dev.

Key facts

What we have checked

Input price
$0.030 per million tokens
Checked OpenRouter models API
Output price
$0.130 per million tokens
Checked OpenRouter models API
Price on akashml
$0.0090 per million cached input tokens
Checked OpenRouter models API
Price on akashml
$0.018 per million input tokens
Checked OpenRouter models API
Price on akashml
$0.090 per million output tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.070 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.150 per million output tokens
Checked OpenRouter models API
Price on coreweave
$0.030 per million cached input tokens
Checked OpenRouter models API
Price on coreweave
$0.030 per million input tokens
Checked OpenRouter models API
Gpqa diamond
60.8% (for 5 Aug 2025)
Checked Epoch AI (CC BY 4.0)
Terminal bench
3.4% (for 5 Aug 2025)
Checked Epoch AI (CC BY 4.0)
Dtbench
68% (for 5 Aug 2025)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via other with model id `accounts/fireworks/models/gpt-oss-20b`.

  • other · accounts/fireworks/models/gpt-oss-20b

Price

What GPT OSS 20B costs, over time

Input price

$0.030 to $0.030

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.130 to $0.130

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
akashmlCached input$0.0090 per million cached input tokensSince 11 Nov 2026No change recordedOpenRouter models API
akashmlInput$0.018 per million input tokensSince 11 Nov 20261 changeOpenRouter models API
akashmlOutput$0.090 per million output tokensSince 11 Nov 20261 changeOpenRouter models API
amazon-bedrockInput$0.070 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockOutput$0.150 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveCached input$0.030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveOutput$0.130 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomCached input$0.0090 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomInput$0.018 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomOutput$0.090 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.140 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmCached input$0.029 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmInput$0.029 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmOutput$0.140 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.070 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqCached input$0.037 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqInput$0.075 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqOutput$0.300 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.020 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$0.150 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
prime-intellectCached input$0.021 per million cached input tokensSince 11 Nov 20263 changesOpenRouter models API
prime-intellectInput$0.023 per million input tokensSince 11 Nov 20264 changesOpenRouter models API
prime-intellectOutput$0.034 per million output tokensSince 11 Nov 20264 changesOpenRouter models API
siliconflowInput$0.040 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$0.180 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much GPT OSS 20B is used

Tokens served a day

27.5B to 25.2B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How GPT OSS 20B scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index10indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index20.7indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index1.2indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,288EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)933EloAs of 10 Nov 2026Design Arena via OpenRouter
Dtbench (best-across-versions)68percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)60.8percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)14.5percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated65.3percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Terminal bench (best-across-versions)3.4percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)40.9percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Compare

Compare GPT OSS 20B side by side

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.018 to 0.021

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 0.03 to 0.034

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.02 to 0.023

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 0.1 to 0.09

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.02 to 0.018

    Source: OpenRouter models API

  6. Price changed

    cached input per mtok: 0.003 to 0.018

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.018 to 0.03

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.004 to 0.02

    Source: OpenRouter models API

  9. Price changed

    cached input per mtok: 0.014 to 0.003

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 0.063 to 0.018

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.015 to 0.004

    Source: OpenRouter models API

  12. Price changed

    output per mtok: 0.018 to 0.063

    Source: OpenRouter models API

  13. Price changed

    input per mtok: 0.004 to 0.015

    Source: OpenRouter models API

  14. Price changed

    output per mtok: 0.09 to 0.13

    Source: OpenRouter models API

  15. Price changed

    input per mtok: 0.018 to 0.03

    Source: OpenRouter models API

  16. Price changed

    output per mtok: 0.13 to 0.09

    Source: OpenRouter models API

  17. Price changed

    input per mtok: 0.03 to 0.018

    Source: OpenRouter models API

  18. Price changed

    output per mtok: 0.14 to 0.13

    Source: OpenRouter models API

  19. Price changed

    input per mtok: 0.029 to 0.03

    Source: OpenRouter models API

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GPT OSS 20B.

No longer listed by its catalogue; the facts shown are as last listed. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperAccounts
Exact model identifieraccounts/fireworks/models/gpt-oss-20b
InputNot established
OutputNot established
Tool calling
Not established
Structured output
Not established
Reasoning controls
Not established
Availability
unknown
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
Not established
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
Not established
Listed retirement date
Not established
Last listed by its catalogue
13 Jul 2026

Not in the models.dev catalogue when checked; last listed 2026-07-13. Retirement is not confirmed by a source.

Inspect the sources and their scope
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Understand the capabilitiesRead the model guide ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 14.9 (2026-07-21) ↗Coding Index: 20.7 (2026-07-21) ↗Agentic Index: 3.1 (2026-07-21) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →