Models/AI Model Directory - API Pricing & Comparison

AI Model Directory - API Pricing & Comparison

65results
ModelUptimePricingActions
G
GPT-5.3 Codex Spark

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

OpenAITextToolsStreaming
InputCredit 2.50
OutputCredit 10.00
Cache readCredit 0.0000
GPT-5.4 Mini

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

OpenAITextVisionToolsStreaming
InputCredit 2.50
OutputCredit 10.00
Cache readCredit 0.0000
GPT-5.4

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

OpenAITextVisionToolsStreaming
InputCredit 2.50
OutputCredit 10.00
Cache readCredit 0.0000
DeepSeek V4 Flash

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

DeepSeekTextToolsStreaming
99.1%4.3 t/s1.2s
InputCredit 14.00
OutputCredit 28.00
Cache readCredit 1.40
Q
Qwen Plus

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

AlibabaTextStreaming
InputCredit 11.11
OutputCredit 27.78
Cache readCredit 2.22
Qwen Image 2.0

Visual generation route optimized for prompt fidelity and creative iteration.

AlibabaImageVision
Free
GPT-5.5

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

OpenAITextVisionToolsStreaming
InputCredit 2.50
OutputCredit 10.00
Cache readCredit 0.0000
C
Cosyvoice V3 Flash

Audio route tuned for responsive speech or voice generation workflows.

DeepSeekAudio
InputCredit 13.89
W
Wan2.7 Image

Visual generation route optimized for prompt fidelity and creative iteration.

AlibabaImage
InputCredit 0.0000
OutputCredit 4.00
Seedance 2.0

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

ByteDance SeedVideoVision
Free
Seedance 2.0 Fast

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

ByteDance SeedVideoVision
Free
Qwen Image 2.0 Pro

Visual generation route optimized for prompt fidelity and creative iteration.

AlibabaImageVision
OutputCredit 30.00
BiRefNet_lite

Visual generation route optimized for prompt fidelity and creative iteration.

Model providerImage
OutputCredit 0.01
GPT 5.6 Luna

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

OpenAITextVisionToolsStreaming
100.0%3.3 t/s1.6s
InputCredit 12.00
OutputCredit 72.00
Cache readCredit 1.20
GPT Image 2

Visual generation route optimized for prompt fidelity and creative iteration.

OpenAIImageVision
100.0%31.5 t/s115.4s
OutputCredit 1.60
DeepSeek V4 Pro

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

DeepSeekReasoningTextToolsStreaming
N/A
GPT 5.6 Terra

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

OpenAITextVisionToolsStreaming
100.0%20.1 t/s9.3s
InputCredit 29.00
OutputCredit 175.00
Cache readCredit 2.90
GPT 5.6 Sol

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

OpenAITextVisionToolsStreaming
InputCredit 35.00
OutputCredit 210.00
Cache readCredit 3.50
D
Doubao Seed 2.0 Lite

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

ByteDanceTextVisionToolsStreaming
InputCredit 60.00
OutputCredit 380.00
Cache readCredit 0.0000
s
seedream-5.0-lite

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

ByteDanceTextVision
OutputCredit 38.00
S
Seedream-4.5

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

ByteDanceTextVision
OutputCredit 45.00
G
GLM-5.2

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

ByteDanceTextToolsStreaming
0.0%0.2s
InputCredit 150.00
OutputCredit 480.00
Cache readCredit 0.0000
G
GFPGAN

Visual generation route optimized for prompt fidelity and creative iteration.

Model providerImage
N/A
R
Real-ESRGAN

Visual generation route optimized for prompt fidelity and creative iteration.

Model providerImage
N/A
Claude Sonnet 4.6

Strong long-context reasoning model with dependable analytical depth.

AnthropicReasoningTextVisionTools
100.0%1.8 t/s2.1s
InputCredit 300.00
OutputCredit 1500.00
Cache readCredit 30.00
C
Claude Sonnet 4

Strong long-context reasoning model with dependable analytical depth.

AnthropicReasoningTextVisionTools
N/A
D
DeepSeek V3.2

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

DeepSeekTextStreaming
N/A
N/A
G
GPT-5.3 Codex

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

OpenAITextVisionToolsStreaming
N/A
N/A
W
Wan2.2 T2v Plus

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

AlibabaVideo
OutputCredit 9.72
W
Wan2.6 T2v

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

AlibabaVideo
N/A
D
DeepSeek Reasoner

Budget-friendly reasoning route for analysis-heavy and coding-heavy workloads.

DeepSeekReasoningTextToolsStreaming
N/A
N/A
D
Doubao Seed 1.8

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

ByteDanceReasoningTextVisionTools
N/A
N/A
D
Doubao Seed 2.0 Mini

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

ByteDanceReasoningTextVisionTools
N/A
N/A
D
Doubao Seed 2.0 Pro

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

ByteDanceReasoningTextVisionTools
N/A
N/A
D
Doubao Seed 1.6

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

ByteDanceTextVisionToolsStreaming
N/A
N/A
D
Doubao Seed 1.6 Flash

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

ByteDanceTextVisionToolsStreaming
N/A
N/A
D
Doubao Seed 2.0 Code

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

ByteDanceTextToolsStreaming
N/A
N/A
D
Doubao Seed Character

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

ByteDanceTextStreaming
N/A
N/A
D
Doubao Seed Code

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

ByteDanceTextToolsStreaming
N/A
N/A
G
GLM 4.7

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

Model providerTextStreaming
N/A
N/A
G
GLM 5.1

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

Model providerTextStreaming
N/A
N/A
K
Kimi K2.5

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

Model providerTextStreaming
N/A
N/A
K
Kimi K2.6

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

Model providerTextStreaming
N/A
N/A
K
Kimi K2.7 Code

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

Model providerTextToolsStreaming
N/A
N/A
M
MiniMax M2.5

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

Model providerTextStreaming
N/A
N/A
M
MiniMax M2.7

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

Model providerTextStreaming
N/A
N/A
M
MiniMax M3

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

Model providerTextStreaming
N/A
N/A
D
Doubao Seedance 1.0 Lite I2V

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

ByteDance SeedVideoVision
N/A
N/A
D
Doubao Seedance 1.0 Lite T2V

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

ByteDance SeedVideo
N/A
N/A
D
Doubao Seedance 1.0 Pro I2V

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

ByteDance SeedVideoVision
N/A
N/A
D
Doubao Seedance 1.0 Pro T2V

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

ByteDance SeedVideo
N/A
N/A
D
Doubao Seedance 1.5 Pro

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

ByteDance SeedVideoVision
N/A
N/A
D
Doubao Seedance 2.0

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

ByteDance SeedVideoVision
N/A
N/A
C
CosyVoice v2

Audio route tuned for responsive speech or voice generation workflows.

Model providerAudio
N/A
N/A
D
Doubao Seed ASR 2.0

Audio route tuned for responsive speech or voice generation workflows.

ByteDanceAudio
N/A
N/A
D
Doubao Embedding Text

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

ByteDanceEmbedding
N/A
N/A
D
Doubao Embedding Vision

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

ByteDanceEmbeddingVision
N/A
N/A
D
Doubao Embedding Vision

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

ByteDanceEmbeddingVision
N/A
N/A
D
Doubao Seedream 4.0

Visual generation route optimized for prompt fidelity and creative iteration.

ByteDanceImage
N/A
N/A