gpt-oss-120b
The cheapest provider for gpt-oss-120b is CoreWeave at $0.065 per 1M tokens (blended), charging $0.03 per 1M input and $0.17 per 1M output tokens. 20 providers serve it; the most expensive charges 6.9× as much. Context window: 128K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.065
at CoreWeave
Input / output
$0.03 / $0.17
per 1M tokens
Providers
20
6.9× spread
7 days
—
best price
30 days
—
best price
Context
128K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
CoreWeaveCheapest fp4 | $0.03 | $0.17 | $0.065 | best | |||
| bf16 | $0.03 | $0.18 | $0.0675 | +4% | |||
| bf16 | $0.037 | $0.17 | $0.0703 | +8% | |||
| bf16 | $0.037 | $0.187 | $0.0745 | +15% | |||
| bf16 | $0.05 | $0.25 | $0.10 | +54% | |||
| fp4 | $0.05 | $0.25 | $0.10 | +54% | |||
| fp8 | $0.045 | $0.275 | $0.103 | +58% | |||
| $0.06 | $0.42 | $0.15 | +131% | ||||
Googleglobal | $0.09 | $0.36 | $0.158 | +142% | |||
| fp4 | $0.10 | $0.50 | $0.20 | +208% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
Amazon Bedrockeu-west-1 | $0.15 | $0.60 | $0.263 | +304% | |||
DeepInfraturbo bf16 | $0.15 | $0.60 | $0.263 | +304% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
| fp4 | $0.15 | $0.60 | $0.263 | +304% | |||
| fp4 | $0.10 | $0.75 | $0.263 | +304% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
| fp8 | $0.15 | $0.60 | $0.263 | +304% | |||
| $0.15 | $0.60 | $0.263 | +304% | ||||
| $0.15 | $0.75 | $0.30 | +362% | ||||
| $0.14 | $0.95 | $0.343 | +427% | ||||
| fp16 | $0.35 | $0.75 | $0.45 | +592% |
- CoreWeaveCheapest$0.065$0.03 in · $0.17 outbest128K ctx99.0% uptimefp4
- $0.0675$0.03 in · $0.18 out+4%128K ctx99.5% uptimebf16
- $0.0703$0.037 in · $0.17 out+8%128K ctx94.5% uptimebf16
- $0.0745$0.037 in · $0.187 out+15%128K ctx100% uptimebf16
- $0.10$0.05 in · $0.25 out+54%128K ctx99.9% uptimebf16
- $0.10$0.05 in · $0.25 out+54%128K ctx97.6% uptimefp4
- $0.103$0.045 in · $0.275 out+58%128K ctx96.9% uptimefp8
- $0.15$0.06 in · $0.42 out+131%125K ctx100% uptime
- global$0.158$0.09 in · $0.36 out+142%128K ctx54.8% uptime
- $0.20$0.10 in · $0.50 out+208%128K ctx100% uptimefp4
- $0.263$0.15 in · $0.60 out+304%128K ctx99.4% uptime
- eu-west-1$0.263$0.15 in · $0.60 out+304%128K ctx100% uptime
- turbo$0.263$0.15 in · $0.60 out+304%128K ctx100% uptimebf16
- $0.263$0.15 in · $0.60 out+304%128K ctx98.8% uptime
- $0.263$0.15 in · $0.60 out+304%128K ctx93.9% uptimefp4
- $0.263$0.10 in · $0.75 out+304%128K ctx100% uptimefp4
- $0.263$0.15 in · $0.60 out+304%128K ctx99.2% uptime
- $0.263$0.15 in · $0.60 out+304%128K ctx77.3% uptimefp8
- $0.263$0.15 in · $0.60 out+304%128K ctx92.6% uptime
- $0.30$0.15 in · $0.75 out+362%128K ctx92.5% uptime
- $0.343$0.14 in · $0.95 out+427%128K ctx99.1% uptime
- $0.45$0.35 in · $0.75 out+592%128K ctx100% uptimefp16
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| CoreWeave, DekaLLM | $0.03 |
| AkashML | $0.037 |
| Crusoe | $0.05 |
| DigitalOcean | $0.012 |
| BaseTen | $0.10 |
| Groq, SiliconFlow | $0.075 |
| Parasail | $0.055 |
| Cerebras | $0.35 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
- Released
- Aug 5, 2025
- First tracked
- Oct 3, 2026
- Canonical slug
- openai/gpt-oss-120b
- Weights
- openai/gpt-oss-120b