CanalAPI

100 AI models behind one API

Access leading global and Chinese providers—OpenAI, Anthropic, Google, DeepSeek, Moonshot, Zhipu, Qwen, and more—through a single OpenAI-compatible endpoint.

100 shown · 100 total
100 models
asr-1.0
MiniMax
语音转文字，按实际音频秒数计费。
chat
$0.190/hour audio input
Try now
claude-fable-5
Anthropic
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
VisionFile InputReasoning+4
$15.00/M input tokens
$75.00/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $30.00/M cache write (1h)
  • $18.75/M cache write (5m)
  • $1.50/M cached input tokens
  • $15.00/M input tokens
  • $75.00/M output tokens
  • $75.00/M reasoning tokens
  • $0.015/ web search
Try now
claude-haiku-4-5-20251001
Anthropic
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
VisionFile InputReasoning+4
$1.50/M input tokens
$7.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.875/M cache write (5m)
  • $0.150/M cached input tokens
  • $1.50/M input tokens
  • $7.50/M output tokens
  • $7.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-1-20250805
Anthropic
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
VisionFile InputReasoning+4
$22.50/M input tokens
$112.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $28.125/M cache write (5m)
  • $2.25/M cached input tokens
  • $22.50/M input tokens
  • $112.50/M output tokens
  • $112.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-20250514
Anthropic
Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...
VisionFile InputReasoning+4
$22.50/M input tokens
$112.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $28.125/M cache write (5m)
  • $2.25/M cached input tokens
  • $22.50/M input tokens
  • $112.50/M output tokens
  • $112.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-5-20251101
Anthropic
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
VisionFile InputReasoning+4
$7.50/M input tokens
$37.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $9.375/M cache write (5m)
  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $37.50/M output tokens
  • $37.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-6
Anthropic
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
VisionFile InputReasoning+4
$7.50/M input tokens
$37.50/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $15.00/M cache write (1h)
  • $9.375/M cache write (5m)
  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $37.50/M output tokens
  • $37.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-7
Anthropic
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
VisionFile InputReasoning+4
$7.50/M input tokens
$37.50/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $15.00/M cache write (1h)
  • $9.375/M cache write (5m)
  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $37.50/M output tokens
  • $37.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-4-8
Anthropic
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
VisionFile InputReasoning+4
$7.50/M input tokens
$37.50/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $15.00/M cache write (1h)
  • $9.375/M cache write (5m)
  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $37.50/M output tokens
  • $37.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-opus-5
Anthropic
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
VisionReasoningFunction Calling+2
$7.50/M input tokens
$37.50/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $15.00/M cache write (1h)
  • $9.375/M cache write (5m)
  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $37.50/M output tokens
  • $37.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-sonnet-4-20250514
Anthropic
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
VisionFile InputReasoning+4
$4.50/M input tokens
$22.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $5.625/M cache write (5m)
  • $0.450/M cached input tokens
  • $4.50/M input tokens
  • $22.50/M output tokens
  • $22.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-sonnet-4-5-20250929
Anthropic
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
VisionFile InputReasoning+5
$4.50/M input tokens
$22.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $5.625/M cache write (5m)
  • $0.450/M cached input tokens
  • $4.50/M input tokens
  • $22.50/M output tokens
  • $22.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-sonnet-4-6
Anthropic
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
VisionFile InputReasoning+4
$4.50/M input tokens
$22.50/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $9.00/M cache write (1h)
  • $5.625/M cache write (5m)
  • $0.450/M cached input tokens
  • $4.50/M input tokens
  • $22.50/M output tokens
  • $22.50/M reasoning tokens
  • $0.015/ web search
Try now
claude-sonnet-5
Anthropic
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
VisionReasoningFunction Calling+2
$3.00/M input tokens
$15.00/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $6.00/M cache write (1h)
  • $3.75/M cache write (5m)
  • $0.300/M cached input tokens
  • $3.00/M input tokens
  • $15.00/M output tokens
  • $15.00/M reasoning tokens
  • $0.015/ web search
Try now
codex-auto-review
Other
面向代码审查的文本推理模型，支持 OpenAI Responses 接口。
Text / CodeReasoningPrompt Caching
$0.300/M input tokens
$1.80/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.030/M cached input tokens
  • $0.300/M input tokens
  • $1.80/M output tokens
  • $1.80/M reasoning tokens
Try now
deep-research-pro-preview-12-2025
Other
VisionStructured OutputWeb Search+1
$3.00/M input tokens
$18.00/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.00165/input image
  • $0.201/output image
  • $180.00image_output_tokens
  • $3.00/M input tokens
  • $18.00/M output tokens
  • $0.0525/ web search
Try now
gemini-2.0-flash
Google
VisionAudio InputVideo Input+5
$0.150/M input tokens
$0.600/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.05audio_input_tokens
  • $0.0375/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.0525/ web search
Try now
gemini-2.0-flash-001
Google
VisionAudio InputVideo Input+5
$0.150/M input tokens
$0.600/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.05audio_input_tokens
  • $0.0375/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.0525/ web search
Try now
gemini-2.0-flash-lite
Google
VisionAudio InputVideo Input+5
$0.1125/M input tokens
$0.450/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1125audio_input_tokens
  • $0.028125/M cached input tokens
  • $0.1125/M input tokens
  • $0.450/M output tokens
  • $0.0525/ web search
Try now
gemini-2.0-flash-lite-001
Google
VisionAudio InputVideo Input+5
$0.1125/M input tokens
$0.450/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1125audio_input_tokens
  • $0.028125/M cached input tokens
  • $0.1125/M input tokens
  • $0.450/M output tokens
  • $0.0525/ web search
Try now
gemini-2.5-computer-use-preview-10-2025
Google
VisionFunction CallingComputer Use
$1.875/M input tokens
$15.00/M output tokens
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.875/M input tokens
  • $3.75/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $15.00/M output tokens
  • $22.50/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-2.5-flash
Google
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
VisionAudio InputVideo Input+6
$0.450/M input tokens
$3.75/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.045/M cached input tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $3.75/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-2.5-flash-image
Google
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...
VisionFile InputImage Generation+5
Per-image pricing
Try now
gemini-2.5-flash-lite
Google
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
VisionAudio InputVideo Input+6
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.450audio_input_tokens
  • $0.015/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-2.5-flash-native-audio-latest
Google
Audio InputAudio Output
$0.450/M input tokens
$3.75/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $0.0525/ web search
Try now
gemini-2.5-flash-native-audio-preview-09-2025
Google
Audio InputAudio Output
$0.450/M input tokens
$3.75/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $0.0525/ web search
Try now
gemini-2.5-flash-native-audio-preview-12-2025
Google
Audio InputAudio Output
$0.450/M input tokens
$3.75/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $0.0525/ web search
Try now
gemini-2.5-flash-preview-tts
Google
Audio Output
$0.450/M input tokens
$3.75/M output tokens
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.450/M input tokens
  • $3.75/M output tokens
  • $0.0525/ web search
Try now
gemini-2.5-pro
Google
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
VisionAudio InputVideo Input+6
$1.875/M input tokens
$15.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cached input tokens
  • $0.375/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.875/M input tokens
  • $1.875/M input tokens

    Priority service

  • $3.75/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $3.75/M input tokens

    Priority service · Total input ≥ 200000 tokens

  • $15.00/M output tokens
  • $15.00/M output tokens

    Priority service

  • $22.50/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $22.50/M output tokens

    Priority service · Total input ≥ 200000 tokens

  • $15.00/M reasoning tokens
  • $15.00/M reasoning tokens

    Priority service

  • $22.50/M reasoning tokens

    Default service · Total input ≥ 200000 tokens

  • $22.50/M reasoning tokens

    Priority service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-2.5-pro-preview-tts
Google
VisionAudio OutputFunction Calling+3
$1.875/M input tokens
$15.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.05audio_input_tokens
  • $0.1875/M cached input tokens
  • $0.375/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.875/M input tokens
  • $3.75/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $15.00/M output tokens
  • $22.50/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-3.1-flash-image-preview
Google
Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...
VisionImage GenerationReasoning+3
Per-image pricing
Try now
gemini-3.1-flash-lite
Google
Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...
VisionAudio InputVideo Input+6
$0.375/M input tokens
$2.25/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.750audio_input_tokens
  • $0.01875/M cached input tokens

    Flex service

  • $0.0375/M cached input tokens
  • $0.0675/M cached input tokens

    Priority service

  • $0.1875/M input tokens

    Flex service

  • $0.375/M input tokens
  • $0.675/M input tokens

    Priority service

  • $1.125/M output tokens

    Flex service

  • $2.25/M output tokens
  • $4.05/M output tokens

    Priority service

  • $2.25/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3.1-flash-lite-preview
Google
Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...
VisionAudio InputVideo Input+6
$0.375/M input tokens
$2.25/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.750audio_input_tokens
  • $0.0375/M cached input tokens
  • $0.375/M input tokens
  • $2.25/M output tokens
  • $2.25/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3.1-flash-live-preview
Google
VisionAudio InputAudio Output+2
$1.125/M input tokens
$6.75/M output tokens
+ 5 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $4.50audio_input_tokens
  • $18.00audio_output_tokens
  • $1.50image_input_tokens
  • $1.125/M input tokens
  • $6.75/M output tokens
  • $0.000050/ input video second
  • $0.0525/ web search
Try now
gemini-3.1-pro-preview
Google
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
VisionAudio InputVideo Input+6
$3.00/M input tokens
$18.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.300/M cached input tokens
  • $0.540/M cached input tokens

    Priority service

  • $0.600/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.08/M cached input tokens

    Priority service · Total input ≥ 200000 tokens

  • $10.80/M input tokens

    Priority service · Total input ≥ 200000 tokens

  • $3.00/M input tokens
  • $5.40/M input tokens

    Priority service

  • $6.00/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $18.00/M output tokens
  • $27.00/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M output tokens

    Priority service

  • $48.60/M output tokens

    Priority service · Total input ≥ 200000 tokens

  • $18.00/M reasoning tokens
  • $27.00/M reasoning tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M reasoning tokens

    Priority service

  • $48.60/M reasoning tokens

    Priority service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-3.1-pro-preview-customtools
Google
Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...
VisionAudio InputVideo Input+6
$3.00/M input tokens
$18.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.300/M cached input tokens
  • $0.540/M cached input tokens

    Priority service

  • $0.600/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.08/M cached input tokens

    Priority service · Total input ≥ 200000 tokens

  • $10.80/M input tokens

    Priority service · Total input ≥ 200000 tokens

  • $3.00/M input tokens
  • $5.40/M input tokens

    Priority service

  • $6.00/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $18.00/M output tokens
  • $27.00/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M output tokens

    Priority service

  • $48.60/M output tokens

    Priority service · Total input ≥ 200000 tokens

  • $18.00/M reasoning tokens
  • $27.00/M reasoning tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M reasoning tokens

    Priority service

  • $48.60/M reasoning tokens

    Priority service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-3.5-flash
Google
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
VisionAudio InputVideo Input+6
$2.25/M input tokens
$13.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $2.70audio_input_tokens

    Priority service

  • $0.225/M cached input tokens
  • $0.405/M cached input tokens

    Priority service

  • $2.25/M input tokens
  • $4.05/M input tokens

    Priority service

  • $13.50/M output tokens
  • $24.30/M output tokens

    Priority service

  • $13.50/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3.5-flash-lite
Google
VisionAudio InputReasoning+4
$0.450/M input tokens
$3.75/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.030/M cached input tokens

    Flex service

  • $0.045/M cached input tokens
  • $0.075/M cached input tokens

    Priority service

  • $0.225/M input tokens

    Flex service

  • $0.450/M input tokens
  • $0.810/M input tokens

    Priority service

  • $1.875/M output tokens

    Flex service

  • $3.75/M output tokens
  • $6.75/M output tokens

    Priority service

  • $3.75/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3.6-flash
Google
VisionAudio InputReasoning+4
$2.25/M input tokens
$11.25/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1125/M cached input tokens

    Flex service

  • $0.225/M cached input tokens
  • $0.405/M cached input tokens

    Priority service

  • $1.125/M input tokens

    Flex service

  • $2.25/M input tokens
  • $4.05/M input tokens

    Priority service

  • $11.25/M output tokens
  • $20.25/M output tokens

    Priority service

  • $5.625/M output tokens

    Flex service

  • $11.25/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3-flash-preview
Google
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
VisionAudio InputVideo Input+6
$0.750/M input tokens
$4.50/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $2.70audio_input_tokens

    Priority service

  • $0.075/M cached input tokens
  • $0.135/M cached input tokens

    Priority service

  • $0.750/M input tokens
  • $1.35/M input tokens

    Priority service

  • $4.50/M output tokens
  • $8.10/M output tokens

    Priority service

  • $4.50/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-3-pro-image-preview
Google
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
VisionImage GenerationReasoning+3
Per-image pricing
Try now
gemini-3-pro-preview
Google
VisionAudio InputVideo Input+6
$3.00/M input tokens
$18.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.300/M cached input tokens
  • $0.540/M cached input tokens

    Priority service

  • $0.600/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.08/M cached input tokens

    Priority service · Total input ≥ 200000 tokens

  • $10.80/M input tokens

    Priority service · Total input ≥ 200000 tokens

  • $3.00/M input tokens
  • $5.40/M input tokens

    Priority service

  • $6.00/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $18.00/M output tokens
  • $27.00/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M output tokens

    Priority service

  • $48.60/M output tokens

    Priority service · Total input ≥ 200000 tokens

  • $18.00/M reasoning tokens
  • $27.00/M reasoning tokens

    Default service · Total input ≥ 200000 tokens

  • $32.40/M reasoning tokens

    Priority service

  • $48.60/M reasoning tokens

    Priority service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-embedding-001
Google
Embedding
$0.225/M input tokens
$0.0525/ web search
Try now
gemini-embedding-2
Google
Embedding
$0.300/M input tokens
$0.000240/sec audio input
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.000240/sec audio input
  • $0.000180/input image
  • $0.300/M input tokens
  • $0.001185/ input video second
  • $0.0525/ web search
Try now
gemini-embedding-2-preview
Google
Embedding
$0.300/M input tokens
$0.000240/sec audio input
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.000240/sec audio input
  • $0.000180/input image
  • $0.300/M input tokens
  • $0.001185/ input video second
  • $0.0525/ web search
Try now
gemini-flash-latest
Google
This model always redirects to the latest model in the Google Gemini Flash family.
VisionAudio InputVideo Input+6
$0.450/M input tokens
$3.75/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.045/M cached input tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $3.75/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-flash-lite-latest
Google
VisionAudio InputVideo Input+6
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.450audio_input_tokens
  • $0.0375/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.0525/ web search
Try now
gemini-pro-latest
Google
This model always redirects to the latest model in the Google Gemini Pro family.
VisionAudio InputVideo Input+6
$1.875/M input tokens
$15.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cached input tokens
  • $0.375/M cached input tokens

    Default service · Total input ≥ 200000 tokens

  • $1.875/M input tokens
  • $3.75/M input tokens

    Default service · Total input ≥ 200000 tokens

  • $15.00/M output tokens
  • $22.50/M output tokens

    Default service · Total input ≥ 200000 tokens

  • $15.00/M reasoning tokens
  • $22.50/M reasoning tokens

    Default service · Total input ≥ 200000 tokens

  • $0.0525/ web search
Try now
gemini-robotics-er-1.5-preview
Google
VisionReasoningFunction Calling+2
$0.450/M input tokens
$3.75/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.50audio_input_tokens
  • $0.450/M input tokens
  • $3.75/M output tokens
  • $3.75/M reasoning tokens
  • $0.0525/ web search
Try now
gpt-5.5
OpenAI
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
VisionFile InputReasoning+4
$7.50/M input tokens
$45.00/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.750/M cached input tokens
  • $7.50/M input tokens
  • $45.00/M output tokens
  • $45.00/M reasoning tokens
Try now
gpt-5.6
OpenAI
VisionFile InputReasoning+4
$6.00/M input tokens
$30.00/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.300/M cached input tokens

    Flex service

  • $0.600/M cached input tokens
  • $0.600/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.20/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $1.20/M cached input tokens

    Priority service

  • $2.40/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $12.00/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $12.00/M input tokens

    Priority service

  • $24.00/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $3.00/M input tokens

    Flex service

  • $6.00/M input tokens
  • $6.00/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $15.00/M output tokens

    Flex service

  • $22.50/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $30.00/M output tokens
  • $45.00/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $60.00/M output tokens

    Priority service

  • $90.00/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $15.00/M reasoning tokens

    Flex service

  • $22.50/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $30.00/M reasoning tokens
  • $45.00/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $60.00/M reasoning tokens

    Priority service

  • $90.00/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

Try now
gpt-5.6-luna
OpenAI
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
VisionFile InputReasoning+4
$0.300/M input tokens
$1.80/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.015/M cached input tokens

    Flex service

  • $0.030/M cached input tokens
  • $0.030/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $0.060/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $0.060/M cached input tokens

    Priority service

  • $0.120/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $0.150/M input tokens

    Flex service

  • $0.300/M input tokens
  • $0.300/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $0.600/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $0.600/M input tokens

    Priority service

  • $1.20/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $0.900/M output tokens

    Flex service

  • $1.35/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.80/M output tokens
  • $2.70/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $3.60/M output tokens

    Priority service

  • $5.40/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $0.900/M reasoning tokens

    Flex service

  • $1.35/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.80/M reasoning tokens
  • $2.70/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $3.60/M reasoning tokens

    Priority service

  • $5.40/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

Try now
gpt-5.6-sol
OpenAI
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
VisionFile InputReasoning+5
$6.00/M input tokens
$30.00/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.300/M cached input tokens

    Flex service

  • $0.600/M cached input tokens
  • $0.600/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.20/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $1.20/M cached input tokens

    Priority service

  • $2.40/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $12.00/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $12.00/M input tokens

    Priority service

  • $24.00/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $3.00/M input tokens

    Flex service

  • $6.00/M input tokens
  • $6.00/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $15.00/M output tokens

    Flex service

  • $22.50/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $30.00/M output tokens
  • $45.00/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $60.00/M output tokens

    Priority service

  • $90.00/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $15.00/M reasoning tokens

    Flex service

  • $22.50/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $30.00/M reasoning tokens
  • $45.00/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $60.00/M reasoning tokens

    Priority service

  • $90.00/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

Try now
gpt-5.6-terra
OpenAI
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
VisionFile InputReasoning+4
$3.00/M input tokens
$18.00/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.150/M cached input tokens

    Flex service

  • $0.300/M cached input tokens
  • $0.300/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $0.600/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $0.600/M cached input tokens

    Priority service

  • $1.20/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $1.50/M input tokens

    Flex service

  • $12.00/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $3.00/M input tokens
  • $3.00/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $6.00/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $6.00/M input tokens

    Priority service

  • $13.50/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $18.00/M output tokens
  • $27.00/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $36.00/M output tokens

    Priority service

  • $54.00/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $9.00/M output tokens

    Flex service

  • $13.50/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $18.00/M reasoning tokens
  • $27.00/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $36.00/M reasoning tokens

    Priority service

  • $54.00/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

  • $9.00/M reasoning tokens

    Flex service

Try now
gpt-6
OpenAI
GPT-6 文本推理模型，支持 OpenAI Responses 接口。
Text / CodeReasoningPrompt Caching
$5.00/M input tokens
$25.00/M output tokens
+ 2 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.250/M cached input tokens

    Flex service

  • $0.500/M cached input tokens
  • $0.500/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.00/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $1.00/M cached input tokens

    Priority service

  • $2.00/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $10.00/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $10.00/M input tokens

    Priority service

  • $2.50/M input tokens

    Flex service

  • $20.00/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $5.00/M input tokens
  • $5.00/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $12.50/M output tokens

    Flex service

  • $18.75/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $25.00/M output tokens
  • $37.50/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $50.00/M output tokens

    Priority service

  • $75.00/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $12.50/M reasoning tokens

    Flex service

  • $18.75/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $25.00/M reasoning tokens
  • $37.50/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $50.00/M reasoning tokens

    Priority service

  • $75.00/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

Try now
gpt-6-astra
OpenAI
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
VisionFile InputReasoning+5
$5.00/M input tokens
$25.00/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.250/M cached input tokens

    Flex service · Total input ≤ 271999 tokens

  • $0.500/M cached input tokens

    Default service · Total input ≤ 271999 tokens

  • $0.500/M cached input tokens

    Flex service · Total input ≥ 272000 tokens

  • $1.00/M cached input tokens

    Default service · Total input ≥ 272000 tokens

  • $1.00/M cached input tokens

    Priority service · Total input ≤ 271999 tokens

  • $2.00/M cached input tokens

    Priority service · Total input ≥ 272000 tokens

  • $0.335/output image

    1K

  • $0.5025/output image

    2K

  • $0.670/output image

    4K

  • $10.00/M input tokens

    Default service · Total input ≥ 272000 tokens

  • $10.00/M input tokens

    Priority service · Total input ≤ 271999 tokens

  • $2.50/M input tokens

    Flex service · Total input ≤ 271999 tokens

  • $20.00/M input tokens

    Priority service · Total input ≥ 272000 tokens

  • $5.00/M input tokens

    Default service · Total input ≤ 271999 tokens

  • $5.00/M input tokens

    Flex service · Total input ≥ 272000 tokens

  • $12.50/M output tokens

    Flex service · Total input ≤ 271999 tokens

  • $18.75/M output tokens

    Flex service · Total input ≥ 272000 tokens

  • $25.00/M output tokens

    Default service · Total input ≤ 271999 tokens

  • $37.50/M output tokens

    Default service · Total input ≥ 272000 tokens

  • $50.00/M output tokens

    Priority service · Total input ≤ 271999 tokens

  • $75.00/M output tokens

    Priority service · Total input ≥ 272000 tokens

  • $12.50/M reasoning tokens

    Flex service · Total input ≤ 271999 tokens

  • $18.75/M reasoning tokens

    Flex service · Total input ≥ 272000 tokens

  • $25.00/M reasoning tokens

    Default service · Total input ≤ 271999 tokens

  • $37.50/M reasoning tokens

    Default service · Total input ≥ 272000 tokens

  • $50.00/M reasoning tokens

    Priority service · Total input ≤ 271999 tokens

  • $75.00/M reasoning tokens

    Priority service · Total input ≥ 272000 tokens

Try now
gpt-image-1
OpenAI
VisionImage Generation
Per-image pricing
Try now
gpt-image-1.5
OpenAI
VisionFile InputImage Generation
Per-image pricing
Try now
gpt-image-2
OpenAI
VisionFile InputImage Generation
Per-image pricing
Try now
gpt-image-2.5-flare
OpenAI
VisionFile InputImage Generation
Per-image pricing
Try now
gpt-image-2.5-sunburst
OpenAI
VisionFile InputImage Generation
Per-image pricing
Try now
image-01
MiniMax
图像生成，按实际成功生成的图片张数计费。
Image Generation
Per-image pricing
Try now
image-01-live
MiniMax
支持人物参考的图像生成，按实际成功生成的图片张数计费。
Image Generation
Per-image pricing
Try now
imagen-4.0-fast-generate-001
Other
Image Generation
Per-image pricing
Try now
imagen-4.0-generate-001
Other
Image Generation
Per-image pricing
Try now
imagen-4.0-ultra-generate-001
Other
Image Generation
Per-image pricing
Try now
jev-1.13.0
Jev
Typed decisions
Decision APIPOST /v1/systemone · text only, not a chat model
$0.0504/M input tokens
$0/M output tokens
Try now
jev-latest
Jev
Typed decisions
Decision APIPOST /v1/systemone · text only, not a chat model
$0.0504/M input tokens
$0/M output tokens
Try now
jev-preview
Jev
Typed decisions
Decision APIPOST /v1/systemone · text only, not a chat model
$0.0504/M input tokens
$0/M output tokens
Try now
M2-her
MiniMax
面向角色扮演与沉浸式对话的文本模型，按实际输入和输出 token 用量计费。
chat
$0.150/M input tokens
$0.600/M output tokens
Try now
MiniMax-H3
MiniMax
MiniMax H3 文生视频，按分辨率与输出秒数计费
Video Generation
From $0.040/ output video second
From $0.040/ input video second
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.020/input image

    First 5 input images free; each additional image is charged

  • $0.040/ input video second

    768P

  • $0.065/ input video second

    2K

  • $0.040/ output video second

    768P

  • $0.065/ output video second

    2K

Try now
MiniMax-H3-Context-IR
MiniMax
整理视频生成上下文与提示，按实际输入和输出 token 用量计费。
Video Generation
$0.450/M input tokens
$1.80/M output tokens
Try now
MiniMax-H3-Max
MiniMax
MiniMax H3-Max 文生视频，按分辨率与输出秒数计费
Video Generation
From $0.025/ output video second
From $0.02765/ input video second
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.037/input image

    First 2 input images free; each additional image is charged

  • $0.02765/ input video second

    480P

  • $0.0715/ input video second

    768P

  • $0.025/ output video second

    480P

  • $0.040/ output video second

    768P

Try now
MiniMax-H3-Regeneration
MiniMax
视频再生成，按实际输入和输出视频时长及参考图片张数计费。
Video Generation
From $0.025/ output video second
From $0.025/ input video second
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.0125/input image

    First 5 input images free; each additional image is charged

  • $0.025/ input video second

    2K

  • $0.025/ output video second

    2K

Try now
MiniMax-Hailuo-02
MiniMax
支持文字或图片输入的视频生成，按实际生成视频时长计费。
Video Generation
From $0.450/ output video minute
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.450/ output video minute

    512P · 10s video

  • $0.500/ output video minute

    512P · 6s video

  • $1.40/ output video minute

    768P · 6s video

  • $1.68/ output video minute

    768P · 10s video

  • $2.45/ output video minute

    1080P · 6s video

Try now
MiniMax-Hailuo-2.3
MiniMax
支持文字或图片输入的视频生成，按实际生成视频时长计费。
Video Generation
From $1.40/ output video minute
Price tiers

The request specifications and usage determine the applicable rate.

  • $1.40/ output video minute

    768P · 6s video

  • $1.68/ output video minute

    768P · 10s video

  • $2.45/ output video minute

    1080P · 6s video

Try now
MiniMax-Hailuo-2.3-Fast
MiniMax
快速图片转视频，按实际生成视频时长计费。
Video Generation
From $0.950/ output video minute
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.950/ output video minute

    768P · 6s video

  • $0.960/ output video minute

    768P · 10s video

  • $1.65/ output video minute

    1080P · 6s video

Try now
MiniMax-M2
MiniMax
通用文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.015/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.1
MiniMax
通用文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.015/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.1-highspeed
MiniMax
高速文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.300/M input tokens
$1.20/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.015/M cached input tokens
  • $0.300/M input tokens
  • $1.20/M output tokens
  • $1.20/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.5
MiniMax
通用文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.015/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.5-highspeed
MiniMax
高速文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.300/M input tokens
$1.20/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.015/M cached input tokens
  • $0.300/M input tokens
  • $1.20/M output tokens
  • $1.20/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.7
MiniMax
通用文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.150/M input tokens
$0.600/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.030/M cached input tokens
  • $0.150/M input tokens
  • $0.600/M output tokens
  • $0.600/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M2.7-highspeed
MiniMax
高速文本生成与对话模型，适用于编程和推理；按实际 token 用量计费。
chat
$0.300/M input tokens
$1.20/M output tokens
+ 4 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.1875/M cache write (5m)
  • $0.030/M cached input tokens
  • $0.300/M input tokens
  • $1.20/M output tokens
  • $1.20/M reasoning tokens
  • $0.005/ web search
Try now
MiniMax-M3
MiniMax
支持文本、图片和视频输入的多模态模型；按实际 token 用量计费，搜索按实际调用次数计费。
chat
$0.150/M input tokens
$0.600/M output tokens
+ 3 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $0.030/M cached input tokens

    Default service · Total input ≤ 512000 tokens

  • $0.045/M cached input tokens

    Priority service · Total input ≤ 512000 tokens

  • $0.060/M cached input tokens

    Default service · Total input ≥ 512001 tokens

  • $0.090/M cached input tokens

    Priority service · Total input ≥ 512001 tokens

  • $0.150/M input tokens

    Default service · Total input ≤ 512000 tokens

  • $0.225/M input tokens

    Priority service · Total input ≤ 512000 tokens

  • $0.300/M input tokens

    Default service · Total input ≥ 512001 tokens

  • $0.450/M input tokens

    Priority service · Total input ≥ 512001 tokens

  • $0.600/M output tokens

    Default service · Total input ≤ 512000 tokens

  • $0.900/M output tokens

    Priority service · Total input ≤ 512000 tokens

  • $1.20/M output tokens

    Default service · Total input ≥ 512001 tokens

  • $1.80/M output tokens

    Priority service · Total input ≥ 512001 tokens

  • $0.600/M reasoning tokens

    Default service · Total input ≤ 512000 tokens

  • $0.900/M reasoning tokens

    Priority service · Total input ≤ 512000 tokens

  • $1.20/M reasoning tokens

    Default service · Total input ≥ 512001 tokens

  • $1.80/M reasoning tokens

    Priority service · Total input ≥ 512001 tokens

  • $0.005/ web search

    Default service

Try now
MiniMax-Voice-Design
MiniMax
通过文字描述设计音色；预览按实际字符数计费，生成音色首次用于语音合成时另计音色费。
chat
$30.00/million input characters
Try now
speech-01-hd
MiniMax
高清文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$50.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $50.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-01-turbo
MiniMax
快速文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$30.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $30.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-02-hd
MiniMax
高清文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$50.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $50.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-02-turbo
MiniMax
快速文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$30.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $30.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-2.6-hd
MiniMax
高清文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$50.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $50.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-2.6-turbo
MiniMax
快速文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$30.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $30.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-2.8-hd
MiniMax
高清文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$50.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $50.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
speech-2.8-turbo
MiniMax
快速文字转语音，按实际字符数计费；私有音色首次启用另计音色费。
chat
$30.00/million input characters
$0.750/cloned voice (first use)
+ 1 more
Price tiers

The request specifications and usage determine the applicable rate.

  • $30.00/million input characters
  • $0.750/cloned voice (first use)
  • $1.50/designed voice (first use)
Try now
veo-2.0-generate-001
Other
chat
$0.525/ output video second
$0.0525/ web search
Try now
veo-3.0-fast-generate-001
Other
chat
$0.225/ output video second
$0.0525/ web search
Try now
veo-3.0-generate-001
Other
chat
$0.600/ output video second
$0.0525/ web search
Try now
veo-3.1-fast-generate-preview
Other
chat
$0.225/ output video second
$0.0525/ web search
Try now
veo-3.1-generate-preview
Other
chat
$0.600/ output video second
$0.0525/ web search
Try now
veo-3.1-lite-generate-preview
Other
chat
$0.075/ output video second
$0.0525/ web search
Try now