Models & Pricing

OpenAI10

GPT 6.1 Sol

Healthy

5/6 sources1M

Plus, K12 and others

Price₫3,000₫10,000in · out, per 1M tokensCache −40%read ₫1,800 · write ₫5,000

Context: 1.1M
Max output: 128K
P95 latency: 15 s

GPT 6 Astra

Degraded

1/2 sources

Price₫8,000₫40,000in · out, per 1M tokensCache −50%read ₫4,000 · write ₫20,000

Context: 1M
Max output: 128K
P95 latency: 713 ms

GPT 6 Sol

Healthy

5/6 sources

Price₫3,000₫5,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 4.3 s

GPT 6 Luna

Healthy

2/3 sources

Price₫500₫1,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 3.6 s

GPT 5.6 Sol

Unavailable

0/1 sources

Price₫2,000₫4,000in · out, per 1M tokensCache −50%read ₫1,000 · write ₫2,000

Context: 1M
Max output: 128K
P95 latency: 1.9 s

GPT 5.6 Terra

Healthy

1/1 sources

Price₫800₫2,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 3.3 s

GPT 5.6 Luna

Healthy

3/4 sources

Price₫25per request

Context: 1M
Max output: 128K
P95 latency: 12.3 s

GPT Image 2.5 Sunburst

Healthy

1/1 sources

Price₫500per image

Context: 128K
Max output: —
P95 latency: 15.1 s

Image generation

Claude9

Claude Opus 5.5

Healthy

4/4 sources

Price₫4,000₫15,000in · out, per 1M tokensCache −25%read ₫3,000 · write ₫5,000

Context: 1M
Max output: 128K
P95 latency: 11.1 s

Claude Sonnet 5.5

Healthy

3/3 sources

Price₫2,400₫10,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 12 s

Claude Haiku 5.5

Healthy

1/1 sources

Price₫1,000₫3,000in · out, per 1M tokensCache −20%read ₫800 · write ₫2,000

Context: 1M
Max output: 128K
P95 latency: 14.5 s

Claude Opus 5

Healthy

3/3 sources

Price₫4,000₫15,000in · out, per 1M tokensCache −50%read ₫2,000 · write ₫4,000

Context: 1M
Max output: 128K
P95 latency: 19.1 s

Claude Opus 4.8

Healthy

2/2 sources

Price₫4,000₫3,000in · out, per 1M tokensCache −50%read ₫2,000 · write ₫15,000

Context: 1M
Max output: 128K
P95 latency: 8.7 s

Claude Opus 4.6

Unavailable

0/1 sources1M

Price₫1,000₫5,000in · out, per 1M tokensCache −50%read ₫500 · write ₫2,000

Context: 1M
Max output: 128K
P95 latency: 12.9 s

Claude Sonnet 4.6

Unavailable

0/1 sources1M

Price₫1,000₫2,000in · out, per 1M tokensCache −75%read ₫250 · write ₫500

Context: 1M
Max output: 128K
P95 latency: 3 s

Claude Sonnet 4.5

Healthy

1/1 sources

Price₫800₫1,500in · out, per 1M tokens

Context: 1M
Max output: 128K

OpenAI Cheap3

GPT 6 Astra Cheap

Healthy

3/3 sources

Price₫2,200₫5,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 23.9 s

GPT 6 Sol Cheap

Healthy

3/3 sources

Price₫1,600₫4,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 24.7 s

GPT 5.6 Sol Cheap

Healthy

3/3 sources

Price₫1,200₫4,000in · out, per 1M tokens

Context: 1M
Max output: 128K

Claude Cheap3

Claude Fable 5 Cheap

Healthy

1/1 sources

Price₫2,000₫5,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 12.3 s

Claude Opus 5.5 Cheap

Healthy

2/2 sources

Price₫1,800₫4,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 23.2 s

Claude Opus 5 Cheap

Healthy

2/2 sources

Price₫1,600₫4,000in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 17.9 s

Gemini8

Gemini

Healthy

System combo4/4 sources

Includes

Gemini 3.8 Flash High
Gemini 3.1 Pro
Gemini 3.7 Flash
Gemini 3.6 Flash

Price₫50per request

Context: 1M
Max output: 65K
P95 latency: 15.4 s

Chat

Gemini 4 Argon

Healthy

3/3 sources

Price₫1,200₫6,000in · out, per 1M tokensCache −8%read ₫1,100 · write ₫4,000

Context: 1M
Max output: 128K
P95 latency: 22.9 s

Gemini 3.8 Flash High

Healthy

1/1 sources

Price₫55per request

Context: 1M
Max output: 128K
P95 latency: 19.5 s

Gemini 3.1 Pro

Healthy

1/1 sources

Price₫50per request

Context: 1M
Max output: 65K
P95 latency: 18.6 s

Gemini 3.7 Flash

Healthy

1/1 sources

Price₫20per request

Context: 1M
Max output: 65K
P95 latency: 5.2 s

Gemini 3.6 Flash

Healthy

1/1 sources

Price₫20per request

Context: 1M
Max output: 65K
P95 latency: 14 s

Gemini 3.1 Flash Image

Healthy

1/1 sources

Price₫100per image

Context: 128K
Max output: 32K
P95 latency: 33.4 s

Image generation

Gemini Veo 3.1 Lite

Healthy

1/1 sources

Price₫500per video

Context: 1K
Max output: —

Video generation

Qwen3

Qwen3.8-max 30đ

Healthy

1/1 sources

Price₫30per request

Context: 1M
Max output: 128K
P95 latency: 9.3 s

Chat
Structured output
Tool calling
Web fetch
Web search

Qwen3.8-max 40đ

Healthy

2/2 sources

Price₫40per request

Context: 1M
Max output: 128K
P95 latency: 19.7 s

Chat
Structured output
Tool calling
Web fetch
Web search

Qwen3 Coder Next

Healthy

1/1 sources

Price₫2per request

Context: 250K
Max output: 250K

Chat
Structured output
Tool calling
Web fetch
Web search

Nvidia1

Nvidia Nemotron 3 Ultra 550B

Healthy

2/2 sources

Price₫150₫200in · out, per 1M tokens

Context: 1M
Max output: 128K
P95 latency: 12.8 s

Chat
Structured output
Tool calling
Web fetch
Web search

Minimax1

Minimax M3

Healthy

1/1 sources

Price₫2per request

Context: 1M
Max output: 128K

Chat
Structured output
Tool calling
Web fetch
Web search

Z.AI2

GLM 5.3

Healthy

1/1 sources

Price₫5per request

Context: —
Max output: —

Chat
Structured output
Tool calling
Web fetch
Web search

GLM 5.2

Healthy

1/1 sources

Price₫2per request

Context: 1M
Max output: 128K
P95 latency: 13.7 s

Chat
Structured output
Tool calling
Web fetch
Web search

Grok1

Grok 4.5

Healthy

1/1 sources

Price₫2per request

Context: 500K
Max output: 64K
P95 latency: 15 s

DeepSeek4

DeepSeek V4 Pro Max

Healthy

1/1 sources

Price₫1,000₫2,000in · out, per 1M tokens

Context: 1M
Max output: 128K

Chat
Structured output
Tool calling
Web fetch
Web search

DeepSeek V4 Pro Max Req

Healthy

3/3 sources

Price₫66per request

Context: 1M
Max output: 128K

Chat
Structured output
Tool calling
Web fetch
Web search

DeepSeek V4 Pro

Healthy

1/1 sources

Price₫25per request

Context: 1M
Max output: 384K
P95 latency: 8.5 s

Chat
Structured output
Tool calling
Web fetch
Web search

DeepSeek V4.1 Flash

Healthy

3/3 sources

Price₫19per request

Context: 1M
Max output: 384K
P95 latency: 10.4 s

Chat
Structured output
Tool calling
Web fetch
Web search

Moonshot AI1

Kimi K3

Healthy

1/1 sources

Price₫500₫1,000in · out, per 1M tokens

Context: 1M
Max output: 1M

OpenAI10

GPT 6.1 Sol

GPT 6 Astra

GPT 6 Sol

GPT 6 Luna

GPT 5.6 Sol

GPT 5.6 Terra

GPT 5.6 Luna

GPT Image 2.5 Sunburst

GPT Image 2.5 Flare

GPT OSS 120B

Claude9

Claude Opus 5.5

Claude Sonnet 5.5

Claude Haiku 5.5

Claude Opus 5

Claude Opus 4.8

Claude Opus 4.6

Claude Sonnet 4.6

Claude Sonnet 4.5

Claude Haiku 4.5

OpenAI Cheap3

GPT 6 Astra Cheap

GPT 6 Sol Cheap

GPT 5.6 Sol Cheap

Claude Cheap3

Claude Fable 5 Cheap

Claude Opus 5.5 Cheap

Claude Opus 5 Cheap

Gemini8

Gemini

Gemini 4 Argon

Gemini 3.8 Flash High

Gemini 3.1 Pro

Gemini 3.7 Flash

Gemini 3.6 Flash

Gemini 3.1 Flash Image

Gemini Veo 3.1 Lite

Qwen3

Qwen3.8-max 30đ

Qwen3.8-max 40đ

Qwen3 Coder Next

Nvidia1

Nvidia Nemotron 3 Ultra 550B

Minimax1

Minimax M3

Z.AI2

GLM 5.3

GLM 5.2

Grok1

Grok 4.5

DeepSeek4

DeepSeek V4 Pro Max

DeepSeek V4 Pro Max Req

DeepSeek V4 Pro

DeepSeek V4.1 Flash

Moonshot AI1

Kimi K3