Models/AI Model Directory - API Pricing & Comparison

AI Model Directory - API Pricing & Comparison

63results

ModelContextPricing

Claude Sonnet 590% OFF

Strong long-context reasoning model with dependable analytical depth.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context1M

Input$0.20/ 1M~~$2.00~~

Output$1.00/ 1M~~$10.00~~

Cache read$0.0200/ 1M~~$0.20~~

Cache write$0.25/ 1M~~$2.50~~

DeepSeek V4 Pro50.3% OFF

High-throughput lane optimized for fast turnaround and cost efficiency.

DDeepSeekRReasoningTText▧Vision⚙Tools

Context1M

Input$0.33/ 1M tokens~~$0.67~~

Output$1.00/ 1M tokens~~$2.02~~

Cache read$0.0112/ 1M tokens~~$0.0225~~

Claude Sonnet 5.585% OFF

Strong long-context reasoning model with dependable analytical depth.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context200K

Input$0.30/ 1M~~$2.00~~

Output$1.50/ 1M~~$10.00~~

Cache read$0.0150/ 1M~~$0.10~~

Cache write$0.38/ 1M~~$2.50~~

DeepSeek V4.1 Flash60% OFF

High-throughput lane optimized for fast turnaround and cost efficiency.

DDeepSeekTText▧Vision⚙Tools⚡Streaming

Context1M

Input$0.0599/ 1M~~$0.15~~

Output$0.24/ 1M~~$0.60~~

Cache read$0.0012/ 1M~~$0.0030~~

DeepSeek V4 Flash

High-throughput lane optimized for fast turnaround and cost efficiency.

DDeepSeekTText▧Vision⚙Tools⚡Streaming

Context1M

Input$0.18/ 1M

Output$0.71/ 1M

Cache read$0.0036/ 1M

Qwen3.8-27B44.3% OFF

Qwen3.8-27B is an open-source, 27-billion-parameter dense multimodal large language model developed by the Alibaba Cloud Qwen team. As a "lightweight powerhouse" within the Qwen3.8 family, it packs robust capabilities—spanning software engineering, "Computer Use" (direct computer interaction), and long-duration office agent tasks—into a footprint suitable for local deployment on a single consumer-grade GPU (such as the RTX 3090 or 4090). It is widely acclaimed in the community as a "local advanced intelligent model."

AAlibabaTText▧Vision⚙Tools⚡Streaming

Context65.5K

Input$0.25/ 1M~~$0.45~~

Output$2.00/ 1M

Cache read$0.0450/ 1M~~$0.0898~~

GPT-5.593% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.35/ 1M~~$5.00~~

Output$2.10/ 1M~~$30.00~~

Cache read$0.0350/ 1M~~$0.50~~

Qwen Plus

Balanced model lane with live routing fallback and production-friendly defaults.

AAlibabaTText⚡Streaming{}JSON

Context996K

Input$0.11/ 1M tokens

Output$0.28/ 1M tokens

Cache read$0.0222/ 1M tokens

Cache write$0.14/ 1M tokens

GPT-6 Sol93% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context922K

Input$0.14/ 1M~~$2.00~~

Output$0.70/ 1M~~$10.00~~

Cache read$0.0140/ 1M~~$0.20~~

Cache write$0.17/ 1M~~$2.50~~

GLM 5.3 Flash60% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.0600/ 1M~~$0.15~~

Output$0.20/ 1M~~$0.50~~

Cache read$0.0120/ 1M~~$0.0300~~

GPT 6.1 Terra93% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context922K

Input$0.0700/ 1M~~$1.00~~

Output$0.35/ 1M~~$5.00~~

Cache read$0.0035/ 1M~~$0.0500~~

Cache write$0.0875/ 1M~~$1.25~~

GPT 5.6 Terra93% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.14/ 1M~~$2.00~~

Output$0.84/ 1M~~$12.00~~

Cache read$0.0140/ 1M~~$0.20~~

Cache write$0.17/ 1M~~$2.50~~

gpt-5.6-luna

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.20/ 1M tokens

Output$1.20/ 1M tokens

Cache read$0.0200/ 1M tokens

Cache write$0.25/ 1M tokens

GPT-6.1 Sol93% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context922K

Input$0.14/ 1M~~$2.00~~

Output$0.70/ 1M~~$10.00~~

Cache read$0.0070/ 1M~~$0.10~~

Cache write$0.17/ 1M~~$2.50~~

Grok 4.693% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context500K

Input$0.14/ 1M tokens~~$2.00~~

Output$0.42/ 1M tokens~~$6.00~~

Cache read$0.0350/ 1M tokens~~$0.50~~

GPT 5.6 Sol93% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.28/ 1M tokens~~$4.00~~

Output$1.40/ 1M tokens~~$20.00~~

Cache read$0.0280/ 1M tokens~~$0.40~~

Cache write$0.35/ 1M tokens~~$5.00~~

Claude Haiku 4.570% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context128K

Input$0.30/ 1M~~$1.00~~

Output$1.50/ 1M~~$5.00~~

Cache read$0.0300/ 1M~~$0.10~~

Cache write$0.38/ 1M~~$1.25~~

Claude Opus 590% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context1M

Input$0.50/ 1M~~$5.00~~

Output$2.50/ 1M~~$25.00~~

Cache read$0.0500/ 1M~~$0.50~~

Cache write$0.63/ 1M~~$6.25~~

Qwen Image 2.0

Visual generation route optimized for prompt fidelity and creative iteration.

AAlibabaIImage▧Vision

Context—

Per output$0.0500/ image

Gemini 3.8 Flash90% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

GGoogleTText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.0750/ 1M~~$0.75~~

Output$0.38/ 1M~~$3.75~~

Cache read$0.0075/ 1M~~$0.0750~~

GLM 5.350% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context1M

Input$0.70/ 1M~~$1.40~~

Output$2.20/ 1M~~$4.40~~

Cache read$0.13/ 1M~~$0.26~~

GPT-6-Astra93% OFF

GPT-6 Astra is our most capable model, built for the hardest end-to-end work. Use it for complex reasoning, coding, computer use, research, and document creation. reasoning.effort supports low, medium, high, xhigh, and max.

OOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.70/ 1M~~$10.00~~

Output$3.50/ 1M~~$50.00~~

Cache read$0.0700/ 1M~~$1.00~~

Cache write$0.88/ 1M~~$12.50~~

Claude Haiku 5.570% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context128K

Input$0.0300/ 1M~~$0.10~~

Output$0.15/ 1M~~$0.50~~

Cache read$0.0030/ 1M~~$0.0100~~

Cache write$0.0375/ 1M~~$0.13~~

Grok 4.593% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context500K

Input$0.14/ 1M~~$2.00~~

Output$0.42/ 1M~~$6.00~~

Cache read$0.0210/ 1M~~$0.30~~

Grok 4.793% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context500K

Input$0.14/ 1M~~$2.00~~

Output$0.42/ 1M~~$6.00~~

Cache read$0.0350/ 1M~~$0.50~~

Claude Sonnet 4.690% OFF

Strong long-context reasoning model with dependable analytical depth.

AAnthropicRReasoningTText▧Vision⚙Tools

Context—

Input$0.30/ 1M tokens~~$3.00~~

Output$1.50/ 1M tokens~~$15.00~~

Cache read$0.0300/ 1M tokens~~$0.30~~

Cache write$0.60/ 1M tokens~~$6.00~~

Gemini 4 Argon90% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

GGoogleTText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$0.20/ 1M~~$2.00~~

Output$1.00/ 1M~~$10.00~~

Cache read$0.0100/ 1M~~$0.10~~

Qwen Image 2.0 Pro

Visual generation route optimized for prompt fidelity and creative iteration.

AAlibabaIImage▧Vision

Context—

Per output$0.30/ image

Wan2.7 Image

Visual generation route optimized for prompt fidelity and creative iteration.

AAlibabaIImage

Context—

Per output$0.0500/ image

1K / default$0.0400/ image

Claude Opus 5.585% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context200K

Input$0.60/ 1M~~$4.00~~

Output$3.00/ 1M~~$20.00~~

Cache read$0.0300/ 1M~~$0.20~~

Cache write$0.75/ 1M~~$5.00~~

Kimi K350.3% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

MModel providerTText▧Vision⚙Tools⚡Streaming

Context1.05M

Input$1.49/ 1M~~$2.99~~

Output$7.44/ 1M~~$14.97~~

Cache read$0.15/ 1M~~$0.30~~

Qwen Image 3.083.3% OFF

Visual generation route optimized for prompt fidelity and creative iteration.

AAlibabaIImage▧Vision

Context—

Per output$0.0300/ image~~$0.18~~

GLM-5.2

Balanced model lane with live routing fallback and production-friendly defaults.

BByteDanceTText⚙Tools⚡Streaming

Context1M

Input$1.50/ 1M tokens

Output$4.80/ 1M tokens

Claude Fable 570% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context1M

Input$3.00/ 1M~~$10.00~~

Output$15.00/ 1M~~$50.00~~

Cache read$0.30/ 1M~~$1.00~~

Cache write$3.75/ 1M~~$12.50~~

Claude Fable 5.170% OFF

Balanced model lane with live routing fallback and production-friendly defaults.

AAnthropicTText▧Vision⚙Tools⚡Streaming

Context200K

Input$3.00/ 1M~~$10.00~~

Output$15.00/ 1M~~$50.00~~

Cache read$0.0750/ 1M~~$0.25~~

Cache write$3.75/ 1M~~$12.50~~

GPT-5.4

Flagship frontier model with balanced reasoning, tool use, and multi-step orchestration.

TTemporarily unavailableOOpenAITText▧Vision⚙Tools⚡Streaming

Context1.05M

Pricing—

GPT-5.4 Mini

Fast and cost-aware general-purpose model for interactive product flows.

TTemporarily unavailableOOpenAITText▧Vision⚙Tools⚡Streaming

Context400K

Pricing—

GPT Image 2

Visual generation route optimized for prompt fidelity and creative iteration.

OOpenAIIImage▧Vision

Context—

Image Input Text Tokens$5.00/ 1M tokens

input_image_tokens$8.00/ 1M tokens

Image Output Tokens$30.00/ 1M tokens

cache_read_text_tokens$1.25/ 1M tokens

cache_read_image_tokens$2.00/ 1M tokens

GPT-5.3 Codex Spark

Coding-first model tuned for structured output, repo work, and agent loops.

TTemporarily unavailableOOpenAITText⚙Tools⚡Streaming

Context—

Pricing—

Wan2.2 T2v Plus

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

480p / 5s$0.0972/ video

Wan2.7 I2v

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

Per second$0.0500/ second

Wan2.7 R2V

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

Per second$0.0500/ second

Wan2.7 T2V

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

Per second$0.0500/ second

Wan2.7 VideoEdit

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

Per second$0.0500/ second

Wan2.6 T2v

Video-capable route for motion-heavy generation and batch rendering.

AAlibabaVVideo

Context—

1080x1920 Duration Seconds$0.14/ second

1088x832 Duration Seconds$0.0833/ second

1232x1664 Duration Seconds$0.14/ second

1248x832 Duration Seconds$0.0833/ second

1280x720 Duration Seconds$0.0833/ second

1664x1232 Duration Seconds$0.14/ second

1920x1080 Duration Seconds$0.14/ second

720x1280 Duration Seconds$0.0833/ second

832x1088 Duration Seconds$0.0833/ second

832x1248 Duration Seconds$0.0833/ second

Doubao Seedance 1.0 Pro Fast

Flagship AI video model for cinematic motion, fast creative iteration, and short-form ad storytelling.

BByteDance SeedVVideo▧Vision

Context—

Output video tokens¥4.20/ 1M tokens

Doubao Seedance 2.5

Flagship AI video model for cinematic motion, fast creative iteration, and short-form ad storytelling.

BByteDance SeedVVideo▧Vision

Context—

Output video tokens (with video input)¥42.00/ 1M tokens

Doubao Seed 2.0 Pro

Reasoning-oriented route designed for deeper analysis and longer prompts.

CComing soonBByteDanceRReasoningTText▧Vision⚙Tools

Context—

Pricing—

Claude Opus 4.8

Balanced model lane with live routing fallback and production-friendly defaults.

TTemporarily unavailableAAnthropicTText▧Vision⚙Tools⚡Streaming

Context1M

Pricing—

Qwen 3.8 Max

Balanced model lane with live routing fallback and production-friendly defaults.

TTemporarily unavailableAAlibabaTText▧Vision⚙Tools⚡Streaming

Context992K

Pricing—

Doubao Seed 1.6

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonBByteDanceTText▧Vision⚙Tools⚡Streaming

Context—

Pricing—

Doubao Seed 1.6 Flash

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonBByteDanceTText▧Vision⚙Tools⚡Streaming

Context—

Pricing—

Doubao Seed 2.0 Lite

Balanced model lane with live routing fallback and production-friendly defaults.

TTemporarily unavailableBByteDanceTText▧Vision⚙Tools⚡Streaming

Context—

Pricing—

Kimi K2.5

Balanced model lane with live routing fallback and production-friendly defaults.

TTemporarily unavailableMModel providerTText▧Vision⚙Tools⚡Streaming

Context—

Pricing—

Doubao Seed 2.0 Code

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonBByteDanceTText⚙Tools⚡Streaming{}JSON

Context—

Pricing—

Doubao Seed Code

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonBByteDanceTText⚙Tools⚡Streaming{}JSON

Context—

Pricing—

Doubao Seed Character

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonBByteDanceTText⚡Streaming{}JSON

Context—

Pricing—

GLM 4.7

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonMModel providerTText⚡Streaming{}JSON

Context—

Pricing—

GLM 5.1

Balanced model lane with live routing fallback and production-friendly defaults.

CComing soonMModel providerTText⚡Streaming{}JSON

Context—

Pricing—

Kimi K2.6

Balanced model lane with live routing fallback and production-friendly defaults.

TTemporarily unavailableMModel providerTText⚡Streaming{}JSON

Context—

Pricing—

Doubao Seedream 4.0

Visual generation route optimized for prompt fidelity and creative iteration.

CComing soonBByteDanceIImage

Context—

Pricing—

GFPGAN

Visual generation route optimized for prompt fidelity and creative iteration.

TTemporarily unavailableMModel providerIImage

Context—

Pricing—

Real-ESRGAN

Visual generation route optimized for prompt fidelity and creative iteration.

TTemporarily unavailableMModel providerIImage

Context—

Pricing—