OpenAI: gpt-oss-20b (batch)
openai/gpt-oss-20b-batchgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license.
Modalities
In / out per 1M$0.02 / $0.11
Context128K
ReleasedAug 5, 2025
Providers
11 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.02 | $0.10 | Variable | 0.55s | 59 tps | 100% | |
 CoreWeavefp4 | $0.03 | $0.13 | $0.03 | 0.13s | 185 tps | 100% |
 Amazon Bedrockeu-west-1 | $0.07 | $0.15 | Variable | 0.43s | 86 tps | 100% |
| Amazon Bedrock | $0.07 | $0.15 | Variable | 0.46s | 351 tps | 100% |
 Darkbloomfp8 | $0.02 | $0.09 | $0.01 | 3.68s | 29 tps | 99.97% |
| $0.03 | $0.14 | $0.03 | 0.44s | 51 tps | 99.97% | |
| $0.03 | $0.15 | $0.02 | 0.47s | 90 tps | 99.97% | |
| $0.07 | $0.30 | $0.04 | 0.32s | 369 tps | 99.86% | |
 DeepInfraus · bf16 | $0.03 | $0.14 | Variable | 0.32s | 88 tps | 99.61% |
 Google Vertexus-central1 | $0.07 | $0.25 | Variable | 0.26s | 259 tps | 98.33% |
 SiliconFlowfp8 | $0.04 | $0.18 | Variable | 1.05s | 41 tps | 86.57% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves gpt-oss-20b (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what gpt-oss-20b (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.02
per 1M tokens
Output
$0.11
per 1M tokens
Cache read
—
not published
Included in every pass
gpt-oss-20b (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.
0.0s5.0s10.0s15.0s20.0s
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
DekaLLM SiliconFlow Groq Darkbloom AkashML Parasail CoreWeave DeepInfra (us) Amazon Bedrock Google Vertex (us-central1) Amazon Bedrock (eu-west-1)
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 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
DekaLLM SiliconFlow Groq Darkbloom AkashML Parasail CoreWeave DeepInfra (us) Amazon Bedrock Google Vertex (us-central1) Amazon Bedrock (eu-west-1)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 96.86%
Oct 16, 11:00 AMNow
Availability over the last 24 hoursAvailability 97.83%
100% 97% 93% 90%
Oct 18, 11:40 AMNow
Apps
Tools that most often run gpt-oss-20b (batch), by tokens this week.
Activity
955.3B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for gpt-oss-20b (batch)?
openai/gpt-oss-20b: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-20b (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-20b (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.02 per 1M input tokens and $0.11 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-20b (batch)?
OpenAI, in the gpt family.
Explore
Other models your pass can call.
