OpenAI: GPT-5.4 (batch)
openai/gpt-5-4-batchGPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.
Modalities
In / out per 1M$1.25 / $7.50
Context1M
ReleasedMar 5, 2026
Providers
7 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $2.50 | $15 | $0.25 | 1.41s | 54 tps | 100% |
 Azureswedencentral | $2.75 | $17 | $0.28 | 0.72s | 66 tps | 100% |
| OpenAI | $5.00 | $30 | $0.50 | 6.00s | 93 tps | 100% |
| Azure | $2.50 | $15 | $0.25 | 6.17s | 39 tps | 99.9% |
| OpenAI | $1.25 | $7.50 | $0.13 | 12.88s | 45 tps | 72.11% |
| Azureeastus2 | $2.75 | $17 | $0.28 | — | — | — |
 Amazon Bedrockus-east-1 | $2.75 | $17 | $0.28 | 1.47s | 81 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GPT-5.4 (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GPT-5.4 (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$1.25
per 1M tokens
Output
$7.50
per 1M tokens
Cache read
$0.13
per 1M cached tokens
Included in every pass
GPT-5.4 (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 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
Azure (swedencentral) Amazon Bedrock (us-east-1) OpenAI Azure OpenAI OpenAI
0 tok/s200 tok/s400 tok/s600 tok/s800 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
OpenAI Azure Amazon Bedrock (us-east-1) OpenAI Azure (swedencentral) OpenAI
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.83%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.76%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run GPT-5.4 (batch), by tokens this week.
Activity
265.2B tokens processed market-wide in the last month.
05.0B10.0B15.0B20.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for GPT-5.4 (batch)?
openai/gpt-5.4:batch. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does GPT-5.4 (batch) hold?
1,050,000 tokens per request, of which up to 128,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does GPT-5.4 (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.25 per 1M input tokens and $7.50 per 1M output tokens.
Who built GPT-5.4 (batch)?
OpenAI, in the GPT family.
Explore
Other models your pass can call.
