GPT-5
gpt-5GPT-5 by OpenAI: 400K context, 128K max output, with Vision, Function Calling, Reasoning, Prompt Caching, Response Schema, Streaming. Via KumoAPI, Input (prompt) costs 1.25 Credits / M tokens.
Capabilities
Listed exactly as the catalog flags them, including what this model does not support.
VisionVision
Natively multimodal: captioning, classification, visual Q&A, chart and screenshot understanding. Images are converted to tokens at the input rate.
Function CallingFunction Calling
Connect the model to external tools and APIs: it decides when to call which function and with what arguments, your code runs it. Force or forbid calls with tool_choice.
ReasoningReasoning
The model thinks before answering, which markedly improves multi-step planning and reasoning for coding, math and data analysis. Thinking tokens bill at the output rate.
Prompt CachingPrompt Caching
Repeated prefixes (system prompts, long documents) hit the cache: reads cost far less than input, writes are priced by retention time.
Response SchemaResponse Schema
Constrain output to a JSON Schema you provide for predictable, type-safe results without parsing free text.
StreamingStreaming
Tokens arrive over SSE as they are generated; the first frame is forwarded immediately with no buffering. Claude Code, Codex and similar tools depend on this.
AudioAudioNot supported
Audio input or speech output.
VideoVideoNot supported
Video input understanding or video generation.
File InputFile InputNot supported
Upload PDFs and other documents directly; the model reads the whole document with native vision.
Web SearchWeb SearchNot supported
Vendor-hosted live web retrieval; the model decides when to search and cites sources.
RealtimeRealtimeNot supported
Bidirectional low-latency voice / text sessions over WebSocket.
SessionSessionNot supported
Server-side multi-turn context (e.g. previous_response_id in Responses) so you need not resend history.
MediaMediaNot supported
Image / video / music generation endpoints.
Multipart FormMultipart FormNot supported
multipart/form-data file-upload requests.
Binary ResponseBinary ResponseNot supported
Endpoints that return raw audio / image bytes.
Full price list
List price → KumoAPI price per channel, every pricing dimension, nothing hidden.
| Item | Unit | OpenAI list price | KumoAPI ×1 |
|---|---|---|---|
| Input (prompt) | per 1M tokens | 1.25 Credits | |
| Output (completion) | per 1M tokens | 10 Credits | |
| Cache read | per 1M tokens | 0.125 Credits |
“Off” is computed at 1 Credit = ¥1 and today’s rate: 1 − channel multiplier × (1 Credit in the list currency). Fast: when request body field service_tier matches ^(fast|priority)$, billed at Cache read ×2、Output (completion) ×2、Input (prompt) ×2、other items ×2; stacks with any channel.
FAQ
How much does the GPT-5 API cost?
Via KumoAPI, Input (prompt) costs 1.25 Credits / M tokens, with 1 Credit = ¥1.
What are the context window and output limit of GPT-5?
Context window 400K tokens, up to 128K tokens per response.
Does GPT-5 support function calling and structured outputs?
Function calling with tool_choice control is supported; structured outputs (JSON Schema) are supported.
One API key for GPT-5 and 30+ models
Free credits on sign-up, pay as you go, no monthly fee.