OpenAI: gpt-oss-120b (batch)
openai/gpt-oss-120b-batchgpt-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$0.03 / $0.14
Context128K
ReleasedAug 5, 2025
Providers
24 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.03 | $0.18 | $0.03 | 0.77s | 21 tps | 100% | |
 DigitalOcean | $0.06 | $0.42 | $0.01 | 0.58s | 49 tps | 100% |
 Basetenus · fp4 | $0.10 | $0.50 | $0.10 | 0.35s | 160 tps | 100% |
| $0.10 | $0.75 | $0.06 | 0.43s | 98 tps | 100% | |
 Amazon Bedrockeu-west-1 | $0.15 | $0.60 | Variable | 0.49s | 138 tps | 100% |
| $0.15 | $0.60 | $0.07 | 0.30s | 301 tps | 100% | |
| $0.35 | $0.75 | $0.35 | 0.35s | 612 tps | 100% | |
 CoreWeavefp4 | $0.03 | $0.17 | $0.03 | 0.35s | 42 tps | 99.97% |
 DeepInfra Turbous · bf16 | $0.15 | $0.60 | Variable | 0.38s | 111 tps | 99.97% |
| Basetenfp4 | $0.10 | $0.50 | $0.10 | 0.39s | 156 tps | 99.89% |
| $0.15 | $0.60 | Variable | 0.37s | 190 tps | 99.81% | |
| $0.14 | $0.95 | Variable | 1.13s | 268 tps | 99.7% | |
| $0.03 | $0.19 | $0.03 | 1.38s | 36 tps | 99.68% | |
| DeepInfraus · bf16 | $0.04 | $0.17 | Variable | 0.64s | 20 tps | 99.65% |
| Amazon Bedrock | $0.15 | $0.60 | Variable | 0.59s | 173 tps | 99.57% |
| $0.03 | $0.15 | $0.03 | 3.33s | 4 tps | 99.28% | |
| $0.05 | $0.25 | Variable | 0.82s | 125 tps | 99.28% | |
| $0.15 | $0.60 | Variable | 1.20s | 108 tps | 99.1% | |
| $0.05 | $0.25 | Variable | 0.85s | 28 tps | 98.88% | |
| $0.05 | $0.25 | $0.05 | 0.29s | 152 tps | 98.54% | |
| $0.15 | $0.75 | Variable | 2.45s | 128 tps | 93.7% | |
| $0.15 | $0.60 | Variable | 0.26s | 70 tps | 91.85% | |
 SiliconFlowfp8 | $0.15 | $0.60 | $0.07 | 2.35s | 7 tps | 80.22% |
 Google Vertexglobal | $0.09 | $0.36 | Variable | 0.53s | 100 tps | 77.48% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves gpt-oss-120b (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what gpt-oss-120b (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.03
per 1M tokens
Output
$0.14
per 1M tokens
Cache read
—
not published
Included in every pass
gpt-oss-120b (batch) 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 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
CoreWeave DeepInfra Turbo (us) DeepInfra (us) DekaLLM AkashML Baseten MARA Parasail Venice Cerebras Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together Amazon Bedrock (eu-west-1)
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
CoreWeave DeepInfra Turbo (us) DeepInfra (us) DekaLLM AkashML Baseten MARA Parasail Venice Cerebras Mancer Phala NovitaAI Nebius Token Factory DigitalOcean SambaNova Baseten (us) Amazon Bedrock Crusoe Google Vertex (global) Groq SiliconFlow Together Amazon Bedrock (eu-west-1)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.5%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.56%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run gpt-oss-120b (batch), by tokens this week.
Activity
2489.2B tokens processed market-wide in the last month.
050.0B100.0B150.0B200.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for gpt-oss-120b (batch)?
openai/gpt-oss-120b:batch. 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 (batch) hold?
131,072 tokens per request, of which up to 117,964 can be the response.
What can it accept and return?
Input: text. Output: text.
What does gpt-oss-120b (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.03 per 1M input tokens and $0.14 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 (batch)?
OpenAI, in the gpt family.
Explore
Other models your pass can call.
