Models · Best cheap
GPT OSS 120B
by Accounts
Open-weight GPT model for self-hosted reasoning and instruction-following workloads.
Our verdict
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.
From the listing
About GPT OSS 120B
Open-weight GPT model for self-hosted reasoning and instruction-following workloads.
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
- Output price
- $0.600 per million tokens
- Price on akashml
- $0.030 per million cached input tokens
- Price on akashml
- $0.030 per million input tokens
- Price on akashml
- $0.187 per million output tokens
- Price on amazon-bedrock
- $0.150 per million input tokens
- Price on amazon-bedrock
- $0.600 per million output tokens
- Price on baseten
- $0.100 per million cached input tokens
- Price on baseten
- $0.100 per million input tokens
- Gpqa diamond
- 75.8% (for 5 Aug 2025)
- Terminal bench
- 18.7% (for 5 Aug 2025)
- Aider polyglot
- 41.8% (for 5 Aug 2025)
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-120b`.
- other ·
accounts/fireworks/models/gpt-oss-120b
Price
What GPT OSS 120B costs, over time
$0.037 to $0.150
$0.170 to $0.600
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| akashmlCached input | $0.030 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| akashmlInput | $0.030 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| akashmlOutput | $0.187 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| amazon-bedrockInput | $0.150 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| amazon-bedrockOutput | $0.600 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| basetenCached input | $0.100 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| basetenInput | $0.100 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| basetenOutput | $0.500 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| cerebrasCached input | $0.350 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| cerebrasInput | $0.350 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| cerebrasOutput | $0.750 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveCached input | $0.030 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveInput | $0.030 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| coreweaveOutput | $0.170 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeCached input | $0.050 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeInput | $0.050 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| crusoeOutput | $0.250 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraCached input | $0.018 per million cached input tokensSince 16 Nov 2026 | No change recorded | OpenRouter models API |
| deepinfraInput | $0.037 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraOutput | $0.170 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmCached input | $0.030 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmInput | $0.030 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| dekallmOutput | $0.180 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| digitaloceanCached input | $0.012 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| digitaloceanInput | $0.060 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| digitaloceanOutput | $0.420 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| google-vertexInput | $0.090 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| google-vertexOutput | $0.360 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| groqCached input | $0.075 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| groqInput | $0.150 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| groqOutput | $0.600 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| io-netCached input | $0.085 per million cached input tokensSince 14 Nov 2026 | 1 change | OpenRouter models API |
| io-netInput | $0.250 per million input tokensSince 14 Nov 2026 | 1 change | OpenRouter models API |
| io-netOutput | $0.450 per million output tokensSince 14 Nov 2026 | 1 change | OpenRouter models API |
| mancerCached input | $0.080 per million cached input tokensSince 17 Nov 2026 | 2 changes | OpenRouter models API |
| mancerInput | $0.080 per million input tokensSince 17 Nov 2026 | 3 changes | OpenRouter models API |
| mancerOutput | $0.375 per million output tokensSince 17 Nov 2026 | 1 change | OpenRouter models API |
| maraInput | $0.150 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| maraOutput | $0.750 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| near-aiCached input | $0.015 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| near-aiInput | $0.030 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| near-aiOutput | $0.150 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusCached input | $0.100 per million cached input tokensSince 27 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusInput | $0.150 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusOutput | $0.600 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| novitaInput | $0.050 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| novitaOutput | $0.250 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailCached input | $0.055 per million cached input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailInput | $0.100 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| parasailOutput | $0.750 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Usage
How much GPT OSS 120B is used
53.7B to 75.6B
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.
| Score | Value | Source | Checked |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 3.8indexAs of 16 Nov 2026 | Artificial Analysis via OpenRouter | |
| Artificial Analysis Coding Index | 30.4indexAs of 16 Nov 2026 | Artificial Analysis via OpenRouter | |
| Artificial Analysis Agentic Index | 3.7indexAs of 16 Nov 2026 | Artificial Analysis via OpenRouter | |
| LMArena text rating (Elo) | 1,366EloAs of 16 Nov 2026 | LMArena (CC-BY-4.0), published 2026-11-11 | |
| Design Arena rating (Elo) | 984EloAs of 16 Nov 2026 | Design Arena via OpenRouter | |
| Aider polyglot (best-across-versions) | 41.8percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Apex agents (best-across-versions) | 4.4percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Dtbench (best-across-versions) | 76.3percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Fiction livebench (best-across-versions) | 44.4percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Gpqa diamond (best-across-versions) | 75.8percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Lech mazur writing (best-across-versions) | 77.1percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Lmca (best-across-versions) | 22.1percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) |
Show 7 more scores
| Score | Value | Source | Checked |
|---|---|---|---|
| Metr time horizons (best-across-versions) | 56.6percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Mystery game puzzles (best-across-versions) | 2percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Otis mock aime 2024 2025 (best-across-versions)Saturated | 88.9percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Simplebench (best-across-versions) | 22.1percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Surface evolver bench (best-across-versions) | 25percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Terminal bench (best-across-versions) | 18.7percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) | |
| Weirdml (best-across-versions) | 48.2percentAs of 5 Aug 2025 | Epoch AI (CC BY 4.0) |
- Saturated
- Top models score close to the maximum, so this test no longer separates them.
Sources
Where this comes from
- OpenRouter models APIThird party
- OpenRouter models APIOfficial
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
- Epoch AI (CC BY 4.0)Third party
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
Price changed
cached input per mtok: 0.044 to 0.104
Price changed
output per mtok: 0.104 to 0.248
Price changed
input per mtok: 0.048 to 0.116
Price changed
cached input per mtok: 0.07 to 0.08
Price changed
output per mtok: 0.25 to 0.375
Price changed
input per mtok: 0.07 to 0.08
Price changed
cached input per mtok: 0.031 to 0.044
Price changed
output per mtok: 0.075 to 0.104
Price changed
input per mtok: 0.035 to 0.048
Price changed
cached input per mtok: 0.032 to 0.031
Price changed
output per mtok: 0.076 to 0.075
Price changed
input per mtok: 0.036 to 0.035
Price changed
cached input per mtok: 0.055 to 0.07
Price changed
input per mtok: 0.055 to 0.07
Price changed
cached input per mtok: 0.069 to 0.032
Price changed
output per mtok: 0.165 to 0.076
Price changed
input per mtok: 0.077 to 0.036
Price changed
cached input per mtok: 0.015 to 0.085
Price changed
output per mtok: 0.15 to 0.45
Price changed
input per mtok: 0.03 to 0.25
In the AI Pulse
Recent daily briefs from the Enterprise DNA AI Pulse that mention this. The short daily read on what is actually happening in AI.
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with GPT OSS 120B.
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-16. Hosting routes and app features can differ.
accounts/fireworks/models/gpt-oss-120b- Tool calling
- Listed support
- Structured output
- Listed support
- Reasoning controls
- Listed support
- Availability
- unknown
- Price basis
- token
- Licence verification
- Check the developer licence; the model name is insufficient
- Context length
- 131K tokens
- Knowledge cutoff
- 1 Jun 2024
- 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
accounts/fireworks/models/gpt-oss-120b: listed by one provider on models.dev (fireworks-ai); a fact is kept only where the listings agree. Hosting routes can differ.
Checked 2026-11-07Source for reasoning controls, tool calling, context length, input, knowledge cutoff, output, structured output.
Checked 2026-11-07Source for last listed.
Checked 2026-07-13FROM 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.
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.
Enter a whole number of runs from 1 to 100,000,000.
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: 16 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) ↗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.