AI models. One API.

Compare pricing, context and capabilities. Connect through one OpenAI-compatible endpoint.

Prices are in USD per 1M tokens.SupportedNot supported

These are text-token rates from the public catalog. Image generation is billed separately; a zero text-output rate does not mean free images. Confirm image pricing and endpoint availability in the Console before use.

Rows labeled Official specifications show provider capabilities and full context. See model details for Gateway request limits and route verification.

Catalog updated: 2026-10-19.

Qwen3.8-27B

Qwen · Free

qwen/qwen3.8-27b
Online$0$0—$0256K128K Free8K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Claude Haiku 5.5

Anthropic · Usage-based

claude-haiku-5-5
Official specifications
Online$0.05$0.005$0.0625$0.251M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GLM-5.3-Flash

Z.ai · Usage-based

z-ai/glm-5.3-flash
Online$0.08$0.023—$0.281M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GPT-6 Luna

OpenAI · Usage-based

gpt-6-luna
Official specifications
Online$0.08$0.008$0.1$0.41.05M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Qwen3.8-Flash

Qwen · Usage-based

qwen/qwen3.8-flash
Online$0.13$0.02—$0.421M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
DeepSeek V4 Flash 0731

DeepSeek · Usage-based

deepseek/deepseek-v4-flash-0731

Legacy alias → DeepSeek V4.1 Flash

Online$0.17$0.005—$0.71M384K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
DeepSeek V4.1 Flash

DeepSeek · Usage-based

deepseek/deepseek-v4.1-flash
Online$0.17$0.005—$0.71M384K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
MiniMax-M2.5

MiniMax · Usage-based

minimax/minimax-m2.5
Online$0.27$0.03—$1.03200K16K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
MiniMax M3

MiniMax · Usage-based

minimax/minimax-m3
Online$0.3$0.05—$1.191M512K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
MiniMax-M2.7

MiniMax · Usage-based

minimax/minimax-m2.7
Online$0.38$0.03—$1.48200K16K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
GLM-5.2

Z.ai · Usage-based

z-ai/glm-5.2
Online$0.53$0.12—$1.721M128K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
Kimi-K2.5

Moonshot AI · Usage-based

moonshotai/kimi-k2.5
Online$0.54$0.06—$2.78256K16K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Gemini 3.8 Flash

Google · Usage-based

gemini/gemini-3.8-flash
Official specifications
Online$0.6$0.06—$31M64K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Kimi K2.7 Code

Moonshot AI · Usage-based

moonshotai/kimi-k2.7-code
Online$0.69$0.15—$3.29256K256K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
DeepSeek V4 Pro

DeepSeek · Usage-based

deepseek/deepseek-v4-pro-0813
Online$0.79$0.026—$2.381M384K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
GLM-5.3

Z.ai · Usage-based

z-ai/glm-5.3
Online$0.82$0.2—$2.881M128K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
Kimi-K2.6

Moonshot AI · Usage-based

moonshotai/kimi-k2.6
Online$0.87$0.07—$3.51256K16K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GLM-5

Z.ai · Usage-based

z-ai/glm-5
Online$0.89$0.11—$3.14200K128K✓ Supported✓ Supported✗ Not supported✓ SupportedIteraCompute
Claude Sonnet 5.5

Anthropic · Usage-based

claude-sonnet-5-5
Official specifications
Online$1$0.05$1.25$51M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GLM-5.1

Z.ai · Usage-based

z-ai/glm-5.1
Online$1.18$0.12—$4.17202K128K✗ Not supported✓ Supported✗ Not supported✓ SupportedIteraCompute
Gemini Nano Banana 2.1

Google · Image model

gemini/gemini-nano-banana-2.1
Official specifications
Online$1.2$0.12—$6128K32K✗ Not supported✓ Supported✓ SupportedNot documentedIteraCompute
Gemini 4 Argon

Google · Usage-based

gemini/gemini-4-argon
Official specifications
Online$1.6$0.08—$81M64K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GPT-6.1 Sol

OpenAI · Usage-based

gpt-6.1-sol
Official specifications
Online$1.6$0.08$2$81.05M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Qwen3.8-2.4T-A95B

Qwen · Usage-based

qwen/qwen3.8-2.4t-a95b
Online$1.95$0.25—$5.71M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Claude Opus 5.5

Anthropic · Usage-based

claude-opus-5-5
Official specifications
Online$2$0.1$2.5$101M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Kimi K3

Moonshot AI · Usage-based

moonshotai/kimi-k3
Online$2.35$0.23—$11.761M1M✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GPT Image 2.5 Flare

OpenAI · Image model

gpt-image-2.5-flare
Official specifications
Online$4$1—$0Not applicableNot applicable✗ Not supportedNot documented✓ Supported✗ Not supportedIteraCompute
GPT Image 2.5 Sunburst

OpenAI · Image model

gpt-image-2.5-sunburst
Official specifications
Online$4$1—$0Not applicableNot applicable✗ Not supportedNot documented✓ Supported✗ Not supportedIteraCompute
Claude Fable 5.1

Anthropic · Usage-based

claude-fable-5-1
Official specifications
Online$5$0.125$6.25$251M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
Claude Mythos 5.1

Anthropic · Usage-based

claude-mythos-5-1
Official specifications
Online$5$0.125$6.25$251M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute
GPT-6 Astra

OpenAI · Usage-based

gpt-6-astra
Official specifications
Online$8$0.8$10$401.05M128K✓ Supported✓ Supported✓ Supported✓ SupportedIteraCompute