Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Gemini 3.1 Flash Lite Image (Google Vertex AI)GoogleRemove
  2. Transcribe 1 ProFish AudioRemove
  3. GLM 5.3Z.AIRemove
gemini-3.1-flash-lite-image-vertex vs transcribe-1-pro vs glm-5.3
AttributeGemini 3.1 Flash Lite Image (Google Vertex AI)gemini-3.1-flash-lite-image-vertexTranscribe 1 Protranscribe-1-proGLM 5.3glm-5.3
Pricing
Request$0.0336 / request——
BillingPay Per Request——
Cache Write (5m)Not applicableNot applicable$1.40 / 1M
Cache Write (1h)Not applicableNot applicable$1.40 / 1M
Cache ReadNot applicableNot applicable$1.40 / 1M
Input—— Not priced per input token$1.40 / 1M
Output—— Not priced per output token$4.40 / 1M
Web Search—$0 / 1M$0 / 1M
Context
Max contextN/AN/A1M
Max outputN/AN/AN/A
Capabilities
VisionYesNoNo
Function CallingNoNoYes
JSON ModeNoNoYes
StreamingNoNoYes
Catalogue
ProviderGoogleFish AudioZ.AI
Categoryimagevoicechat
Charge typePay Per RequestPay As You GoPay As You Go
Released—2026-09-24—
Description
SummaryGemini 3.1 Flash Lite Image served from Google Vertex AI. Billed per image at US$0.0336. Call it through /v1/chat/completions with stream set to false; the image is returned in the message content as a base64 data URI. Maximum output resolution is 1K. A request for a larger size returns a 1K image with the same aspect ratio at the same price. When a size is reduced, the response carries an X-Image-Resolution-Capped header with the requested and delivered size.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.GLM-5.3 is Z.ai's large-scale reasoning model designed for complex software engineering and long-horizon agentic workflows. It supports text input and output with a 1M-token context window, enabling sustained reasoning across large codebases and extended multi-step tasks. Building on GLM-5.2, it delivers stronger coding performance while improving the balance between capability and token efficiency, making it well suited for autonomous coding agents, large-scale engineering workflows, and complex task execution.