Enterprise DNAEnterprise DNA
OpenAI logo

Models · Best cheap

GPT OSS 120B

by Cf

Open GPT reasoning model for self-hosted agents and controllable deployments.

Visit Cf ↗

Our verdict

Not reviewed yet

We have not reviewed GPT OSS 120B 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 120B

Open GPT reasoning model for self-hosted agents and controllable deployments.

Notes

GPT OSS 120B is listed in the EDNA Models directory, sourced from models.dev.

Key facts

What we have checked

Input price
$0.150 per million tokens
Checked OpenRouter models API
Output price
$0.600 per million tokens
Checked OpenRouter models API
Price on akashml
$0.030 per million cached input tokens
Checked OpenRouter models API
Price on akashml
$0.030 per million input tokens
Checked OpenRouter models API
Price on akashml
$0.187 per million output tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.150 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.600 per million output tokens
Checked OpenRouter models API
Price on baseten
$0.100 per million cached input tokens
Checked OpenRouter models API
Price on baseten
$0.100 per million input tokens
Checked OpenRouter models API
Gpqa diamond
75.8% (for 5 Aug 2025)
Checked Epoch AI (CC BY 4.0)
Terminal bench
18.7% (for 5 Aug 2025)
Checked Epoch AI (CC BY 4.0)
Aider polyglot
41.8% (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 `@cf/openai/gpt-oss-120b`.

  • other · @cf/openai/gpt-oss-120b

Price

What GPT OSS 120B costs, over time

Input price

$0.037 to $0.150

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

Source: OpenRouter models API. Checked .

Output price

$0.170 to $0.600

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$0.030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
akashmlInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
akashmlOutput$0.187 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
amazon-bedrockOutput$0.600 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenInput$0.100 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenOutput$0.500 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
cerebrasCached input$0.350 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cerebrasInput$0.350 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cerebrasOutput$0.750 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$0.170 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeInput$0.050 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.037 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.170 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmCached input$0.030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmOutput$0.180 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.012 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.060 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$0.420 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.090 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$0.360 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqCached input$0.075 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
groqOutput$0.600 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
io-netCached input$0.015 per million cached input tokensSince 11 Nov 2026No change recordedOpenRouter models API
io-netInput$0.030 per million input tokensSince 11 Nov 2026No change recordedOpenRouter models API
io-netOutput$0.150 per million output tokensSince 11 Nov 2026No change recordedOpenRouter models API
mancerCached input$0.055 per million cached input tokensSince 7 Nov 2026No change recordedOpenRouter models API
mancerInput$0.055 per million input tokensSince 2 Nov 20261 changeOpenRouter models API
mancerOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
maraInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
maraOutput$0.750 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
near-aiCached input$0.015 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
near-aiInput$0.030 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
near-aiOutput$0.150 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusCached input$0.100 per million cached input tokensSince 27 Oct 2026No change recordedOpenRouter models API
nebiusInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusOutput$0.600 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.050 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$0.250 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.055 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.100 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$0.750 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much GPT OSS 120B is used

Tokens served a day

53.7B to 69B

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 120B 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 Index3.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index30.4indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index3.7indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,365EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)986EloAs of 10 Nov 2026Design Arena via OpenRouter
Aider polyglot (best-across-versions)41.8percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Apex agents (best-across-versions)4.4percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)76.3percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Fiction livebench (best-across-versions)44.4percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)75.8percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Lech mazur writing (best-across-versions)77.1percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Lmca (best-across-versions)22.1percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Show 7 more scores
ScoreValueSourceChecked
Metr time horizons (best-across-versions)56.6percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)2percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated88.9percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)22.1percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Surface evolver bench (best-across-versions)25percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Terminal bench (best-across-versions)18.7percentAs of 5 Aug 2025Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)48.2percentAs 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 120B 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: 0.036 to 0.037

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 0.087 to 0.088

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.04 to 0.041

    Source: OpenRouter models API

  4. Price changed

    cached input per mtok: 0.07 to 0.036

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 0.167 to 0.087

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.078 to 0.04

    Source: OpenRouter models API

  7. Price changed

    cached input per mtok: 0.014 to 0.07

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 0.057 to 0.167

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.015 to 0.078

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 0.087 to 0.6

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.023 to 0.15

    Source: OpenRouter models API

  12. Price changed

    cached input per mtok: 0.039 to 0.014

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 0.159 to 0.057

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.043 to 0.015

    Source: OpenRouter models API

  15. Price changed

    output per mtok: 0.038 to 0.087

    Source: OpenRouter models API

  16. Price changed

    input per mtok: 0.01 to 0.023

    Source: OpenRouter models API

  17. Price changed

    output per mtok: 0.6 to 0.065

    Source: OpenRouter models API

  18. Price changed

    input per mtok: 0.15 to 0.017

    Source: OpenRouter models API

  19. Price changed

    output per mtok: 0.067 to 0.159

    Source: OpenRouter models API

  20. Price changed

    input per mtok: 0.018 to 0.043

    Source: OpenRouter models API

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with GPT OSS 120B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperCf
Exact model identifier@cf/openai/gpt-oss-120b
Inputtext
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
128K tokens
Knowledge cutoff
1 Jun 2024
Developer release date
Not established
First seen in the catalogue
Not established
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

@cf/openai/gpt-oss-120b: listed by one provider on models.dev (cloudflare-workers-ai); a fact is kept only where the listings agree. Hosting routes can differ.

Checked 2026-11-07
models.dev ↗

Source for reasoning controls, tool calling, context length, input, knowledge cutoff, output, structured output.

Checked 2026-11-07
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.

Run a reliable agentWorkflow & starter prompt ↗

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: 23.8 (2026-07-21) ↗Coding Index: 30.4 (2026-07-21) ↗Agentic Index: 13.2 (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 →