OpenAI

GPT OSS 120b API Pricing 2026

Compare pricing, benchmarks, and providers for GPT OSS 120b. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

GPT OSS 120b was released on August 5, 2025. Pricing starts at $0.030 per million input tokens and $0.100 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through OpenAI.

Context Window
131K
tokens
Pricing
Input$0.030
Output$0.100
Cached$0.0045
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
VisionReasoningTools

GPT OSS 120b is priced at $0.030 per million input tokens and $0.100 per million output tokens. It has a context window of 131,072 tokens. It is available from 23 providers, with AkashML the cheapest at $0.030 per million input tokens (input prices range from $0.030 to $0.350). On benchmarks, GPT OSS 120b scores Aider 41.8 (22nd percentile).

Pricing Comparison

Compare GPT OSS 120b with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.030
$0.100
—
—
—
131,072
Try
$0.020
$0.100
—
39.9
16.0
32,768
Try
$0.020
$0.020
—
7.6
3.4
60,000
Try
$0.020
$0.040
—
31.1
8.7
16,384
Try
$0.020
$0.020
—
—
—
32,768
Try
$0.020
$0.096
—
—
74.3
1,000,000
Try
$0.021
$0.063
—
—
—
262,144
Try
$0.025
$0.100
—
—
—
262,144
Try
$0.025
$0.200
—
—
—
400,000
Try
$0.025
$0.100
—
—
—
262,144
Try
$0.028
$0.110
—
—
—
32,768
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

GPT OSS 120b is available from multiple providers with different pricing and availability.

23
Providers
$0.030
Cheapest Input/M
$0.100
Cheapest Output/M
AkashML
Best Price

Provider Pricing

23 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
A
AkashML
Best Price
$0.030
$0.187
$0.030
-
100.0%
V
Venice
Best Price
$0.030
$0.150
$0.030
-
100.0%
D
DekaLLM
Best Price
$0.030
$0.180
$0.030
-
66.7%
C
CoreWeave
Best Price
$0.030
$0.170
$0.030
-
100.0%
FlexAI
FlexAI
Best Price
$0.030
$0.150
$0.004
-
-
$0.037
$0.170
$0.018
-
100.0%
C
Crusoe
$0.050
$0.250
$0.050
-
100.0%
D
DigitalOcean
$0.060
$0.420
$0.012
-
-
M
Mancer 2
$0.085
$0.375
$0.085
-
-
$0.090
$0.360
-
-
100.0%
$0.090
$0.360
-
-
-
$0.100
$0.750
$0.055
-
100.0%
$0.100
$0.500
$0.100
-
-
$0.100
$0.100
$0.450
-
-
$0.140
$0.950
-
-
90.0%
$0.150
$0.600
-
-
-
$0.150
$0.600
$0.075
-
-
$0.150
$0.600
$0.100
-
100.0%
$0.150
$0.600
-
-
96.7%
$0.150
$0.600
$0.075
-
100.0%
P
Phala
$0.150
$0.600
-
-
100.0%
M
Mara
$0.150
$0.750
-
-
100.0%
$0.350
$0.750
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does GPT OSS 120b perform? Vote based on your experience.

Cost vs. Quality

Compare GPT OSS 120b's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try GPT OSS 120b

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test GPT OSS 120b directly in your browser.

Open Playground

Frequently Asked Questions

GPT OSS 120b costs $0.000030 per 1,000 input tokens and $0.000100 per 1,000 output tokens.
GPT OSS 120b is available from 23 providers. AkashML offers the best price.
AkashML offers GPT OSS 120b at $0.030 per million input tokens, the lowest of 23 providers (input prices range from $0.030 to $0.350 per million tokens).
GPT OSS 120b scores Aider 41.8 (22nd percentile). Only benchmarks with published data for this model are shown.
We compare GPT OSS 120b with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All OpenAI Models

See pricing for all OpenAI models.

View all OpenAI models →