Chat and reasoning models

AQA

aqa

AQA for text generation, reasoning, tool calling, and live streaming responses.

Chat Context window: 7,168 tokens Max output: 1,024 tokens

Minimum hold $0.010000

Computer Use Preview

computer-use-preview

Computer Use Preview for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Streaming supported Tool/function calling supported

Input per 1m tokens $1.250000

Output per 1m tokens $10.000000

Minimum hold $0.010000

DeepSeek OCR

DeepSeek-OCR

DeepSeek OCR through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming Context window: 32,768 tokens Max output: 8,192 tokens

Input per 1m tokens $0.560000

Output per 1m tokens $1.680000

Minimum hold $0.010000

DeepSeek R1 0528

DeepSeek-R1-0528

DeepSeek R1 0528 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 163,840 tokens Max output: 32,768 tokens

Input per 1m tokens $1.350000

Output per 1m tokens $5.400000

Minimum hold $0.010000

DeepSeek V3.1

DeepSeek-V3.1

DeepSeek V3.1 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 32,768 tokens

Input per 1m tokens $1.230000

Output per 1m tokens $4.940000

Minimum hold $0.010000

DeepSeek V3.2

DeepSeek-V3.2

DeepSeek V3.2 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 163,840 tokens Max output: 65,536 tokens

Input per 1m tokens $0.560000

Cached input per 1m tokens $0.056000

Output per 1m tokens $1.680000

Gemini 2.5 Flash

gemini-2.5-flash

Gemini 2.5 Flash for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $0.300000

Cached input per 1m tokens $0.030000

Output per 1m tokens $2.500000

Gemini 2.5 Flash-Lite

gemini-2.5-flash-lite

Gemini 2.5 Flash-Lite for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $0.100000

Cached input per 1m tokens $0.010000

Output per 1m tokens $0.400000

Gemini 2.5 Pro

gemini-2.5-pro

Gemini 2.5 Pro for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $1.250000

Cached input per 1m tokens $0.125000

Output per 1m tokens $10.000000

Gemini 3 Flash Preview

gemini-3-flash-preview

Gemini 3 Flash Preview for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $0.500000

Cached input per 1m tokens $0.050000

Output per 1m tokens $3.000000

Gemini 3.1 Flash-Lite

gemini-3.1-flash-lite

Gemini 3.1 Flash-Lite for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $0.250000

Cached input per 1m tokens $0.025000

Output per 1m tokens $1.500000

Gemini 3.1 Pro Preview

gemini-3.1-pro-preview

Gemini 3.1 Pro Preview for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.200000

Output per 1m tokens $12.000000

Gemini 3.1 Pro Preview Custom Tools

gemini-3.1-pro-preview-customtools

Gemini 3.1 Pro Preview Custom Tools for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.200000

Output per 1m tokens $12.000000

Gemini 3.5 Flash

gemini-3.5-flash

Gemini 3.5 Flash for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $1.500000

Cached input per 1m tokens $0.150000

Output per 1m tokens $9.000000

Gemini Flash Latest

gemini-flash-latest

Gemini Flash Latest for text generation, reasoning, tool calling, and streaming responses.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 65,536 tokens

Input per 1m tokens $0.500000

Cached input per 1m tokens $0.050000

Output per 1m tokens $3.000000

Gemini Robotics-ER 1.6 Preview

gemini-robotics-er-1.6-preview

Gemini Robotics-ER 1.6 Preview for text generation, reasoning, tool calling, and streaming responses.

Chat Streaming الأدوات Streaming supported Tool/function calling supported

Input per 1m tokens $1.000000

Output per 1m tokens $5.000000

Minimum hold $0.010000

Gemma 4 26B A4B IT

gemma-4-26b-a4b-it

Gemma 4 26B A4B IT through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 128,000 tokens Max output: 8,192 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $8.000000

GLM 4.7

glm-4.7

GLM 4.7 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 200,000 tokens Max output: 128,000 tokens

Input per 1m tokens $1.000000

Cached input per 1m tokens $0.100000

Output per 1m tokens $3.200000

GLM 4.7 Flash

glm-4.7-flash

GLM 4.7 Flash through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 32,768 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $8.000000

GLM 5

glm-5

GLM 5 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 200,000 tokens Max output: 128,000 tokens

Input per 1m tokens $1.000000

Cached input per 1m tokens $0.100000

Output per 1m tokens $3.200000

GLM 5.2

glm-5.2

GLM 5.2 routed primarily through Azure AI Foundry with Cloudflare Workers AI fallback.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 128,000 tokens

Input per 1m tokens $1.400000

Cached input per 1m tokens $0.260000

Output per 1m tokens $4.400000

GPT Chat Latest

gpt-chat-latest

GPT Chat Latest for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 128,000 tokens Max output: 16,384 tokens

Input per 1m tokens $5.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $30.000000

GPT OSS 120B

gpt-oss-120b

GPT OSS 120B through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 65,536 tokens

Input per 1m tokens $0.150000

Output per 1m tokens $0.600000

Minimum hold $0.010000

GPT OSS 20B

gpt-oss-20b

GPT OSS 20B through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 65,536 tokens

Input per 1m tokens $0.070000

Output per 1m tokens $0.300000

Minimum hold $0.010000

GPT-5

gpt-5

GPT-5 routed primarily through Azure OpenAI with Cloudflare fallback.

Chat Streaming الأدوات Context window: 400,000 tokens Max output: 128,000 tokens

Input per 1m tokens $1.250000

Cached input per 1m tokens $0.125000

Output per 1m tokens $10.000000

GPT-5.1

gpt-5.1

GPT-5.1 for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 400,000 tokens Max output: 128,000 tokens

Input per 1m tokens $1.250000

Cached input per 1m tokens $0.125000

Output per 1m tokens $10.000000

GPT-5.3 Codex

gpt-5.3-codex

GPT-5.3 Codex for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 400,000 tokens Max output: 128,000 tokens

Input per 1m tokens $1.750000

Cached input per 1m tokens $0.175000

Output per 1m tokens $14.000000

GPT-5.4

gpt-5.4

GPT-5.4 for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 922,000 tokens Max output: 128,000 tokens

Input per 1m tokens $2.500000

Cached input per 1m tokens $0.250000

Output per 1m tokens $15.000000

GPT-5.4 Mini

gpt-5.4-mini

GPT-5.4 Mini for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 272,000 tokens Max output: 128,000 tokens

Input per 1m tokens $0.750000

Cached input per 1m tokens $0.075000

Output per 1m tokens $4.500000

GPT-5.4 Pro

gpt-5.4-pro

GPT-5.4 Pro for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 1,050,000 tokens Max output: 128,000 tokens

Input per 1m tokens $30.000000

Output per 1m tokens $180.000000

Minimum hold $0.010000

GPT-5.5

gpt-5.5

GPT-5.5 for language generation, reasoning, tool calling, and streaming chat responses.

Chat Streaming الأدوات Context window: 922,000 tokens Max output: 128,000 tokens

Input per 1m tokens $5.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $30.000000

Grok 4.1 Fast (Non-Reasoning)

grok-4.1-fast-non-reasoning

Grok 4.1 Fast (Non-Reasoning) through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 128,000 tokens Max output: 128,000 tokens

Input per 1m tokens $0.200000

Cached input per 1m tokens $0.050000

Output per 1m tokens $0.500000

Grok 4.1 Fast (Reasoning)

grok-4.1-fast-reasoning

Grok 4.1 Fast (Reasoning) through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 128,000 tokens Max output: 128,000 tokens

Input per 1m tokens $0.200000

Cached input per 1m tokens $0.050000

Output per 1m tokens $0.500000

Grok 4.20 (Non-Reasoning)

grok-4-20-non-reasoning

Grok 4.20 (Non-Reasoning) through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 2,000,000 tokens Max output: 8,192 tokens

Input per 1m tokens $1.250000

Cached input per 1m tokens $0.200000

Output per 1m tokens $2.500000

Grok 4.20 (Reasoning)

grok-4-20-reasoning

Grok 4.20 (Reasoning) through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 2,000,000 tokens Max output: 8,192 tokens

Input per 1m tokens $1.250000

Cached input per 1m tokens $0.200000

Output per 1m tokens $2.500000

Kimi K2 Thinking

Kimi-K2-Thinking

Kimi K2 Thinking through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 65,536 tokens

Input per 1m tokens $1.045000

Cached input per 1m tokens $0.176000

Output per 1m tokens $4.400000

Kimi K2.5

Kimi-K2.5

Kimi K2.5 for text generation, reasoning, tool calling, and live streaming responses.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 262,144 tokens

Input per 1m tokens $0.660000

Cached input per 1m tokens $0.110000

Output per 1m tokens $3.300000

Kimi K2.6

Kimi-K2.6

Kimi K2.6 routed primarily through Azure AI Foundry with Cloudflare Workers AI fallback.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 262,144 tokens

Input per 1m tokens $1.045000

Cached input per 1m tokens $0.176000

Output per 1m tokens $4.400000

Kimi K2.7

Kimi-K2.7

Kimi K2.7 routed primarily through Azure AI Foundry with Cloudflare Workers AI fallback.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 262,144 tokens

Input per 1m tokens $0.950000

Cached input per 1m tokens $0.190000

Output per 1m tokens $4.000000

Llama 3.1 70B Instruct

llama-3.1-70b-instruct

Llama 3.1 70B Instruct through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 128,000 tokens Max output: 8,192 tokens

Minimum hold $0.010000

Llama 3.3 70B Instruct FP8 Fast

llama-3.3-70b-instruct-fp8-fast

Llama 3.3 70B Instruct FP8 Fast through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 128,000 tokens Max output: 8,192 tokens

Minimum hold $0.010000

Meta Llama 3 405B Instruct

llama-3-405b-instruct

Meta Llama 3 405B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 8,192 tokens

Input per 1m tokens $2.700000

Output per 1m tokens $2.700000

Minimum hold $0.010000

Meta Llama 3 70B Instruct

llama-3-70b-instruct

Meta Llama 3 70B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 8,192 tokens Max output: 8,192 tokens

Input per 1m tokens $0.710000

Output per 1m tokens $0.710000

Minimum hold $0.010000

Meta Llama 3 8B Instruct

llama-3-8b-instruct

Meta Llama 3 8B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 8,192 tokens Max output: 8,192 tokens

Input per 1m tokens $0.200000

Output per 1m tokens $0.200000

Minimum hold $0.010000

Meta Llama 3.2 90B Instruct

llama-3.2-90b-instruct

Meta Llama 3.2 90B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 8,192 tokens

Input per 1m tokens $0.900000

Output per 1m tokens $0.900000

Minimum hold $0.010000

Meta Llama 3.3 70B Instruct

Llama-3.3-70B-Instruct

Meta Llama 3.3 70B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 131,072 tokens Max output: 8,192 tokens

Input per 1m tokens $0.710000

Output per 1m tokens $0.710000

Minimum hold $0.010000

Meta Llama 4 Maverick Instruct

Llama-4-Maverick-17B-128E-Instruct-FP8

Meta Llama 4 Maverick Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 524,288 tokens Max output: 8,192 tokens

Input per 1m tokens $0.350000

Output per 1m tokens $1.150000

Minimum hold $0.010000

Meta Llama 4 Scout Instruct

llama-4-scout-17b-16e-instruct

Meta Llama 4 Scout Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 1,048,576 tokens Max output: 8,192 tokens

Input per 1m tokens $0.180000

Output per 1m tokens $0.590000

Minimum hold $0.010000

MiniMax M2

MiniMax-M2

MiniMax M2 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 196,608 tokens Max output: 196,608 tokens

Input per 1m tokens $0.300000

Cached input per 1m tokens $0.030000

Output per 1m tokens $1.200000

Mistral Small 3.1 24B Instruct

mistral-small-3.1-24b-instruct

Mistral Small 3.1 24B Instruct through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 128,000 tokens Max output: 8,192 tokens

Minimum hold $0.010000

Nemotron 3 120B A12B

nemotron-3-120b-a12b

Nemotron 3 120B A12B through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 128,000 tokens Max output: 8,192 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $8.000000

Phi 2

phi-2

Phi 2 through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 2,048 tokens Max output: 2,048 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $8.000000

Qwen2.5 Coder 32B Instruct

qwen2.5-coder-32b-instruct

Qwen2.5 Coder 32B Instruct through Cloudflare Workers AI with Omixa provider routing.

Chat Streaming Context window: 32,768 tokens Max output: 8,192 tokens

Input per 1m tokens $2.000000

Cached input per 1m tokens $0.500000

Output per 1m tokens $8.000000

Qwen3 235B A22B Instruct 2507

qwen3-235b-a22b-instruct-2507

Qwen3 235B A22B Instruct 2507 through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 65,536 tokens

Input per 1m tokens $0.220000

Cached input per 1m tokens $0.022000

Output per 1m tokens $1.800000

Qwen3 Coder 480B A35B Instruct

qwen3-coder-480b-a35b-instruct

Qwen3 Coder 480B A35B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 65,536 tokens

Input per 1m tokens $0.220000

Cached input per 1m tokens $0.022000

Output per 1m tokens $1.800000

Qwen3 Next 80B A3B Instruct

qwen3-next-80b-a3b-instruct

Qwen3 Next 80B A3B Instruct through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 65,536 tokens

Input per 1m tokens $0.220000

Cached input per 1m tokens $0.022000

Output per 1m tokens $1.800000

Qwen3 Next 80B A3B Thinking

qwen3-next-80b-a3b-thinking

Qwen3 Next 80B A3B Thinking through Google Vertex AI Model Garden/MaaS with Omixa routing and streaming.

Chat Streaming الأدوات Context window: 262,144 tokens Max output: 65,536 tokens

Input per 1m tokens $0.220000

Cached input per 1m tokens $0.022000

Output per 1m tokens $1.800000