OpenAI: gpt-oss-120b
openai/gpt-oss-120bgpt-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.
Modalities
In / out per 1M$0.15 / $0.60
Context128K
ReleasedAug 5, 2025
Providers
24 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 NEAR AIfp4 | $0.03 | $0.15 | $0.01 | 0.84s | 39 tps | 100% |
| $0.03 | $0.18 | $0.03 | 0.65s | 34 tps | 100% | |
| $0.03 | $0.19 | $0.03 | 0.44s | 89 tps | 100% | |
 DigitalOcean | $0.06 | $0.42 | $0.01 | 0.63s | 58 tps | 100% |
| $0.10 | $0.75 | $0.06 | 0.57s | 86 tps | 100% | |
 Amazon Bedrockeu-west-1 | $0.15 | $0.60 | Variable | 0.50s | 122 tps | 100% |
| $0.15 | $0.60 | Variable | 0.28s | 307 tps | 100% | |
| Amazon Bedrock | $0.15 | $0.60 | Variable | 0.61s | 133 tps | 100% |
| $0.15 | $0.60 | $0.07 | 0.32s | 267 tps | 100% | |
| $0.35 | $0.75 | $0.35 | 0.29s | 738 tps | 100% | |
 Basetenfp4 | $0.10 | $0.50 | $0.10 | 0.46s | 163 tps | 99.97% |
 CoreWeavefp4 | $0.03 | $0.17 | $0.03 | 0.40s | 41 tps | 99.94% |
| Basetenus · fp4 | $0.10 | $0.50 | $0.10 | 0.42s | 168 tps | 99.94% |
| $0.05 | $0.25 | $0.05 | 0.27s | 260 tps | 99.86% | |
| $0.15 | $0.60 | Variable | 0.98s | 127 tps | 99.82% | |
| $0.03 | $0.15 | $0.03 | 1.81s | 25 tps | 99.74% | |
| $0.05 | $0.25 | Variable | 0.76s | 147 tps | 99.51% | |
| $0.14 | $0.95 | Variable | 1.01s | 381 tps | 99.48% | |
| $0.05 | $0.25 | Variable | 0.62s | 52 tps | 99.39% | |
| $0.15 | $0.75 | Variable | 1.68s | 157 tps | 97.74% | |
 DeepInfraus · bf16 | $0.04 | $0.17 | Variable | 0.62s | 32 tps | 95.33% |
| $0.15 | $0.60 | Variable | 0.25s | 126 tps | 87.65% | |
 SiliconFlowfp8 | $0.15 | $0.60 | $0.07 | 1.21s | 35 tps | 78.56% |
 Google Vertexglobal | $0.09 | $0.36 | Variable | 0.46s | 53 tps | 2.04% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves gpt-oss-120b in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what gpt-oss-120b costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.15
per 1M tokens
Output
$0.60
per 1M tokens
Cache read
$0.07
per 1M cached tokens
Included in every pass
gpt-oss-120b is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
CoreWeave DeepInfra (us) DekaLLM AkashML Baseten MARA Parasail Venice Amazon Bedrock (eu-west-1) Cerebras NEAR AI Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
CoreWeave DeepInfra (us) DekaLLM AkashML Baseten MARA Parasail Venice Amazon Bedrock (eu-west-1) Cerebras NEAR AI Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.08%
Oct 16, 9:00 AMNow
Availability over the last 24 hoursAvailability 98.26%
100% 97% 93% 90%
Oct 18, 9:50 AMNow
Apps
Tools that most often run gpt-oss-120b, by tokens this week.
Activity
2332.0B tokens processed market-wide in the last month.
050.0B100.0B150.0B200.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for gpt-oss-120b?
openai/gpt-oss-120b. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does gpt-oss-120b hold?
131,072 tokens per request, of which up to 65,536 can be the response.
What can it accept and return?
Input: text. Output: text.
What does gpt-oss-120b cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.15 per 1M input tokens and $0.60 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2024. Anything later has to come from your prompt or a tool call.
Who built gpt-oss-120b?
OpenAI, in the gpt family.
Explore
Other models your pass can call.
