Models

Choose from the world’s top AI models

Find the right model by task, capability and cost. One API spec, one bill and smart routing — switching models is no longer an engineering burden.

Production-ready models
74+
Service availability
99.99%
API compatible
OpenAI
OpenAIClaudeGeminiDeepSeekxAIQwenMoonshotVolcengineHunyuanWenxinQingyanCohereSunoXinference

Browse all models

Prices are per million tokens for reference; your console bill is authoritative.

Pricing note: the ≈ line is a local-currency reference; the struck-through amount is the official list price and the amount after it is what you actually pay. All settlement is in Credits.

74 models, showing 74

Claude Fable 5Text

Anthropic · 1M context
claude-fable-5
Input (prompt)
6Credits / M
Output (completion)
30Credits / M
Cache read0.6 Credits / MCache write · 5 min7.5 Credits / M+1 more pricing dimensions — see console
76.1 t/s40% off

Claude Fable 5.1Text

Anthropic · 1M context
claude-fable-5-1
Input (prompt)
6Credits / M
Output (completion)
30Credits / M
Cache read0.15 Credits / MCache write · 5 min7.5 Credits / M+2 more pricing dimensions — see console
64.2 t/s40% off

Claude Haiku 4.5Text

Anthropic · 200K context
claude-haiku-4-5-20251001
Input (prompt)
0.6Credits / M
Output (completion)
3Credits / M
Cache read0.06 Credits / MCache write · 5 min0.75 Credits / M+1 more pricing dimensions — see console
59.8 t/s40% off

Claude Haiku 5.5Text

Anthropic
claude-haiku-5-5
Input (prompt)
0.16Credits / M
Output (completion)
0.8Credits / M
Cache read0.016 Credits / MCache write · 5 min0.2 Credits / M+1 more pricing dimensions — see console
197.4 t/s

Claude Opus 4.5Text

Anthropic · 200K context
claude-opus-4-5-20251101
Input (prompt)
3Credits / M
Output (completion)
15Credits / M
Cache read0.3 Credits / MCache write · 5 min3.75 Credits / M+1 more pricing dimensions — see console
61.3 t/s40% off

Claude Opus 4.6Text

Anthropic · 1M context
claude-opus-4-6
Input (prompt)
3Credits / M
Output (completion)
15Credits / M
Cache read0.3 Credits / MCache write · 5 min3.75 Credits / M+1 more pricing dimensions — see console
59.2 t/s40% off

Claude Opus 4.7Text

Anthropic · 1M context
claude-opus-4-7
Input (prompt)
3Credits / M
Output (completion)
15Credits / M
Cache read0.3 Credits / MCache write · 5 min3.75 Credits / M+1 more pricing dimensions — see console
51.0 t/s40% off

Claude Opus 4.8Text

Anthropic · 1M context
claude-opus-4-8
Input (prompt)
3Credits / M
Output (completion)
15Credits / M
Cache read0.3 Credits / MCache write · 5 min3.75 Credits / M+1 more pricing dimensions — see console
50.5 t/s40% off

Claude Opus 5Text

Anthropic · 1M context
claude-opus-5
Input (prompt)
3Credits / M
Output (completion)
15Credits / M
Cache read0.3 Credits / MCache write · 5 min3.75 Credits / M+1 more pricing dimensions — see console
52.7 t/s40% off

Claude Opus 5.5Text

Anthropic · 1M context
claude-opus-5-5
Input (prompt)
2.4Credits / M
Output (completion)
12Credits / M
Cache read0.12 Credits / MCache write · 5 min3 Credits / M+1 more pricing dimensions — see console
11/2/2026, 6:37:05 AM100.0%
76.6 t/sLatency 1.4s40% off

Claude Sonnet 4.5Text

Anthropic · 200K context
claude-sonnet-4-5-20250929
Input (prompt)
1.8Credits / M
Output (completion)
9Credits / M
Cache read0.18 Credits / MCache write · 5 min2.25 Credits / M+1 more pricing dimensions — see console
0.9 t/s40% off

Claude Sonnet 4.6Text

Anthropic · 1M context
claude-sonnet-4-6
Input (prompt)
1.8Credits / M
Output (completion)
9Credits / M
Cache read0.18 Credits / MCache write · 5 min2.25 Credits / M+1 more pricing dimensions — see console
62.2 t/s40% off

Claude Sonnet 5Text

Anthropic · 1M context
claude-sonnet-5
Input (prompt)
1.2Credits / M
Output (completion)
6Credits / M
Cache read0.12 Credits / MCache write · 5 min1.5 Credits / M+1 more pricing dimensions — see console
7.5 t/s40% off

Claude Sonnet 5.5Text

Anthropic · 1M context
claude-sonnet-5-5
Input (prompt)
3.2Credits / M
Output (completion)
16Credits / M
Cache read0.16 Credits / MCache write · 5 min4 Credits / M+2 more pricing dimensions — see console
11/2/2026, 6:35:35 AM100.0%
99.7 t/sLatency 1.3s

DeepSeek V4.1 FlashText

DeepSeek · 1M context
deepseek-flash
Input (prompt)
0.6Credits / M
Output (completion)
2.4Credits / M
Cache read0.012 Credits / M
11/2/2026, 6:35:36 AM99.9%
107.2 t/sLatency 1.4s40% off

DeepSeek V4 ProText

DeepSeek · 1M context
deepseek-v4-pro
Input (prompt)
4.05Credits / M
Output (completion)
12.15Credits / M
Cache read0.135 Credits / M
11/2/2026, 6:35:39 AM99.8%
67.5 t/sLatency 2.4s10% off

Gemini 2.5 Flash ImageText

Google · 64K context
gemini-2.5-flash-image
Input (prompt)
0.48Credits / M
Output (completion)
4Credits / M
Image output (general)48 Credits / MWeb search (general)22.4 Credits / 1K calls
198.3 t/s

Gemini 3.1 Flash ImageText

Google · 128K context
gemini-3.1-flash-image
Input (prompt)
0.8Credits / M
Output (completion)
4.8Credits / M
Image output (general)96 Credits / MWeb search (general)22.4 Credits / 1K calls
125.7 t/s

Gemini 3.1 Flash-Lite ImageText

Google
gemini-3.1-flash-lite-image
Input (prompt)
0.4Credits / M
Output (completion)
2.4Credits / M
Image output (general)48 Credits / MWeb search (general)22.4 Credits / 1K calls
304.9 t/s

Gemini 3.1 Pro (Preview)Text

Google · 1M context
gemini-3.1-pro-preview
Input (prompt)
3.2Credits / M
Output (completion)
19.2Credits / M
Cache read0.32 Credits / MWeb search (general)22.4 Credits / 1K calls
11/2/2026, 6:38:37 AM93.0%
5.1 t/sLatency 33.6s

Gemini 3.5 FlashText

Google · 1M context
gemini-3.5-flash
Input (prompt)
2.4Credits / M
Output (completion)
14.4Credits / M
Cache read0.24 Credits / MWeb search (general)22.4 Credits / 1K calls+1 more pricing dimensions — see console
165.3 t/s

Gemini 3.5 Flash-LiteText

Google · 1M context
gemini-3.5-flash-lite
Input (prompt)
0.4Credits / M
Output (completion)
2.4Credits / M
Cache read0.04 Credits / MAudio input0.8 Credits / M+1 more pricing dimensions — see console
3.2 t/s

Gemini 3.6 FlashText

Google · 1M context
gemini-3.6-flash
Input (prompt)
1.2Credits / M
Output (completion)
6Credits / M
Cache read0.12 Credits / MCache storage (duration)0.8 Credits / M·hr+2 more pricing dimensions — see console

Gemini 3.7 FlashText

Google · 1M context
gemini-3.7-flash
Input (prompt)
1.2Credits / M
Output (completion)
6Credits / M
Cache read0.12 Credits / MCache storage (duration)0.8 Credits / M·hr+1 more pricing dimensions — see console
90.9 t/s

Gemini 3.8 FlashText

Google · 1M context
gemini-3.8-flash
Input (prompt)
1.2Credits / M
Output (completion)
6Credits / M
Cache read0.12 Credits / MWeb search (general)22.4 Credits / 1K calls
11/2/2026, 6:35:51 AM95.3%
103.8 t/sLatency 12.1s

Gemini 3.8 Flash-Lite TTSText

Google · 8K context
gemini-3.8-flash-lite-tts
Input (prompt)
0.8Credits / M
Audio output9.6 Credits / M

Gemini 3.8 Flash TTSText

Google · 8K context
gemini-3.8-flash-tts
Input (prompt)
0.8Credits / M
Audio output14.4 Credits / M

Gemini 3 Pro ImageText

Google
gemini-3-pro-image
Input (prompt)
3.2Credits / M
Output (completion)
19.2Credits / M
Image output (general)192 Credits / MWeb search (general)22.4 Credits / 1K calls
67.6 t/s

Gemini 4 ArgonText

Google · 1M context
gemini-4-argon
Input (prompt)
3.2Credits / M
Output (completion)
16Credits / M
Cache read0.16 Credits / MWeb search (general)22.4 Credits / 1K calls+1 more pricing dimensions — see console
11/2/2026, 6:37:08 AM85.4%
41.5 t/sLatency 3.2s

Gemini Nano Banana 2.1Text

Google · 128K context
gemini-nano-banana-2.1
Input (prompt)
2.4Credits / M
Output (completion)
12Credits / M
Image output (general)48 Credits / MWeb search (general)22.4 Credits / 1K calls
132.4 t/s

GLM-5.1Text

Zhipu
glm-5.1
Input (prompt)
4.8Credits / M
Output (completion)
16.8Credits / M
Cache read1.2 Credits / M
65.8 t/s40% off

GLM-5.2Text

Zhipu · 1M context
glm-5.2
Input (prompt)
4.8Credits / M
Output (completion)
16.8Credits / M
Cache read1.2 Credits / M
11.9 t/s40% off

GLM-5.3Text

Zhipu · 1M context
glm-5.3
Input (prompt)
4.8Credits / M
Output (completion)
16.8Credits / M
Cache read1.2 Credits / M
7.2 t/s40% off

GLM-5.3-FlashText

Zhipu · 1M context
glm-5.3-flash
Input (prompt)
0.48Credits / M
Output (completion)
1.68Credits / M
Cache read0.138 Credits / M
11/2/2026, 6:37:09 AM94.2%
45.8 t/sLatency 708ms40% off

GLM-5.3-FlashXText

Zhipu · 1M context
glm-5.3-flashx
Input (prompt)
1.2Credits / M
Output (completion)
4.2Credits / M
Cache read3.34 Credits / M
16.8 t/s40% off

GPT-5.6 SolText

OpenAI · 1.05M context
gpt-5.6-sol
Input (prompt)
1.25Credits / M
Output (completion)
7.5Credits / M
Cache read0.125 Credits / M
11/2/2026, 6:37:10 AM99.7%
85.5 t/sLatency 1.1s75% off

GPT-5.6 TerraText

OpenAI · 1.05M context
gpt-5.6-terra
Input (prompt)
0.5Credits / M
Output (completion)
3Credits / M
Cache read0.05 Credits / M
50.2 t/s75% off

GPT-6.1 SolText

OpenAI · 1.05M context
gpt-6.1-sol
Input (prompt)
0.5Credits / M
Output (completion)
2.5Credits / M
Cache read0.025 Credits / MCache write (general)0.625 Credits / M
11/2/2026, 6:37:12 AM99.3%
36.4 t/sLatency 1.8s75% off

GPT-6.1 TerraText

OpenAI · 1.05M context
gpt-6.1-terra
Input (prompt)
0.25Credits / M
Output (completion)
1.25Credits / M
Cache read0.0125 Credits / MCache write (general)0.3125 Credits / M+1 more pricing dimensions — see console
11/2/2026, 6:37:13 AM99.6%
48.8 t/sLatency 1.5s75% off

GPT-6 AstraText

OpenAI · 1.05M context
gpt-6-astra
Input (prompt)
2.5Credits / M
Output (completion)
12.5Credits / M
Cache read0.25 Credits / MCache write (general)3.13 Credits / M
11/2/2026, 6:37:16 AM99.5%
18.7 t/sLatency 2.7s75% off

GPT-6 SolText

OpenAI · 1.05M context
gpt-6-sol
Input (prompt)
0.5Credits / M
Output (completion)
2.5Credits / M
Cache read0.05 Credits / MCache write (general)0.625 Credits / M
11/2/2026, 6:37:18 AM99.8%
32.0 t/sLatency 1.5s75% off

GPT-Image-2Text

OpenAI
gpt-image-2
Input (prompt)
1.25Credits / M
Output (completion)
7.5Credits / M
Cache read0.3125 Credits / MImage input2 Credits / M+2 more pricing dimensions — see console
37.4 t/s75% off

GPT-Image-2.5 FlareText

OpenAI
gpt-image-2.5-flare
Input (prompt)
1.25Credits / M
Output (completion)
7.5Credits / M
Cache read0.3125 Credits / MImage input2 Credits / M+2 more pricing dimensions — see console
25.8 t/s75% off

gpt-image-2.5-flare-cImage

OpenAI
gpt-image-2.5-flare-c
Image output (general)
0.099Credits / image
≈ 0.396 Credits for four images
53.8 t/s

GPT-Image-2.5 SunburstText

OpenAI
gpt-image-2.5-sunburst
Input (prompt)
1.25Credits / M
Output (completion)
7.5Credits / M
Cache read0.3125 Credits / MImage input2 Credits / M+2 more pricing dimensions — see console
25.4 t/s75% off

gpt-image-2.5-sunburst-cImage

OpenAI
gpt-image-2.5-sunburst-c
Image output (general)
0.099Credits / image
≈ 0.396 Credits for four images
43.0 t/s

gpt-image-2-cImage

OpenAI
gpt-image-2-c
Image output (general)
0.099Credits / image
≈ 0.396 Credits for four images
29.4 t/s

Grok 4.20 Multi-Agent BetaText

xAI · 1M context
grok-4.20-multi-agent-0309
Input (prompt)
1.25Credits / M
Output (completion)
2.5Credits / M
Cache read0.2 Credits / M

Grok 4.20 (Non-Reasoning)Text

xAI · 1M context
grok-4.20-non-reasoning
Input (prompt)
1.25Credits / M
Output (completion)
2.5Credits / M
Cache read0.2 Credits / MWeb search (general)5 Credits / 1K calls

Grok 4.20Text

xAI · 1M context
grok-4.20-reasoning
Input (prompt)
1.25Credits / M
Output (completion)
2.5Credits / M
Cache read0.2 Credits / MWeb search (general)5 Credits / 1K calls
96.2 t/s

Grok 4.3Text

xAI · 1M context
grok-4.3
Input (prompt)
1.25Credits / M
Output (completion)
2.5Credits / M
Cache read0.2 Credits / MWeb search (general)5 Credits / 1K calls

Grok 4.5Text

xAI · 500K context
grok-4.5
Input (prompt)
2Credits / M
Output (completion)
6Credits / M
Cache read0.5 Credits / MWeb search (general)5 Credits / 1K calls
8.3 t/s

Grok 4.6Text

xAI · 500K context
grok-4.6
Input (prompt)
2Credits / M
Output (completion)
6Credits / M
Cache read0.5 Credits / MWeb search (general)5 Credits / 1K calls
11/2/2026, 6:37:22 AM99.8%
70.0 t/sLatency 4.0s

Grok 4.7Text

xAI · 500K context
grok-4.7
Input (prompt)
2Credits / M
Output (completion)
6Credits / M
Cache read0.5 Credits / MWeb search (general)5 Credits / 1K calls
11/2/2026, 6:37:23 AM99.9%
54.2 t/sLatency 1.3s

Grok Build 0.1Text

xAI · 256K context
grok-build-0.1
Input (prompt)
1Credits / M
Output (completion)
2Credits / M
Cache read0.2 Credits / M

Grok Imagine ImageImage

xAI
grok-imagine-image
Image output (general)
0.02Credits / image
≈ 0.08 Credits for four images
Image input0.002 Credits / image

Grok Imagine Image 2.0Image

xAI
grok-imagine-image-2.0
Image output · 1K
0.01Credits / image
1K 0.012K 0.06
≈ 0.04 Credits for four images
Image input0.01 Credits / imageImage output (general)0.05 Credits / image

Grok Imagine Quality ModeImage

xAI
grok-imagine-image-quality
Image output · 1K
0.05Credits / image
1K 0.052K 0.07
≈ 0.2 Credits for four images
Image output (general)0.05 Credits / image

Grok Imagine VideoVideo

xAI
grok-imagine-video
Video output (general)
0.05Credits / sec
≈ 0.4 Credits for an 8-second video
Image input0.002 Credits / imageVideo output · 720p0.07 Credits / sec

Grok Imagine Video 1.5Video

xAI
grok-imagine-video-1.5
Video output · 720p
0.14Credits / sec
720P 0.141080P 0.25
≈ 1.12 Credits for an 8-second video
Image input0.01 Credits / MVideo output (general)0.08 Credits / sec

Jev 1.13Text

TypeSafe · 32K context
jev-1.13.0
Input (prompt)
0.2205Credits / M
1153.3 t/s25% off

Jev 1.14Text

TypeSafe · 32K context
jev-1.14.0
Input (prompt)
0.2205Credits / M
11/2/2026, 6:37:23 AM100.0%
305.1 t/sLatency 151ms25% off

Kimi K2.6Text

Kimi · 256K context
kimi-k2.6
Input (prompt)
3.9Credits / M
Output (completion)
16.2Credits / M
Cache read0.66 Credits / M
2.6 t/s40% off

Kimi K2.7 CodeText

Kimi · 256K context
kimi-k2.7-code
Input (prompt)
3.9Credits / M
Output (completion)
16.2Credits / M
Cache read0.06 Credits / M
11/2/2026, 6:37:46 AM94.2%
205.4 t/sLatency 12.1s40% off

Kimi K3Text

Kimi · 1M context
kimi-k3
Input (prompt)
12Credits / M
Output (completion)
60Credits / M
Cache read1.2 Credits / M
11.4 t/s40% off

Kimi K3.1 ProText

Kimi · 1M context
kimi-k3.1-pro
Input (prompt)
7.8Credits / M
Output (completion)
40.8Credits / M
Cache read0.78 Credits / MCache write (general)7.8 Credits / M+1 more pricing dimensions — see console
39.4 t/s40% off

Kimi K3.1 Pro HighspeedText

Kimi · 1M context
kimi-k3.1-pro-highspeed
Input (prompt)
15.6Credits / M
Output (completion)
81.6Credits / M
Cache read0.78 Credits / MCache write (general)15.6 Credits / M+1 more pricing dimensions — see console
5.0 t/s40% off

MiniMax M2.5Text

MiniMax · 200K context
minimax-m2.5
Input (prompt)
1.26Credits / M
Output (completion)
5.04Credits / M
Cache read0.126 Credits / MCache write (general)1.57 Credits / M
4.5 t/s40% off

MiniMax M2.7Text

MiniMax · 200K context
minimax-m2.7
Input (prompt)
1.26Credits / M
Output (completion)
5.04Credits / M
Cache read0.252 Credits / MCache write (general)1.57 Credits / M
4.4 t/s40% off

MiniMax M3Text

MiniMax · 1M context
minimax-m3
Input (prompt)
1.26Credits / M
Output (completion)
5.04Credits / M
Cache read0.252 Credits / M
11/2/2026, 6:38:39 AM70.8%
10.2 t/sLatency 1.9s40% off

MiniMax M3.1 FlashText

MiniMax · 1M context
MiniMax-M3.1-Flash
Input (prompt)
0.6Credits / M
Output (completion)
2.4Credits / M
Cache read0.06 Credits / M
11/2/2026, 6:38:45 AM84.2%
59.2 t/sLatency 5.8s40% off

Qwen3.7 PlusText

Qwen · 1M context
qwen3.7-plus
Input (prompt)
1.4Credits / M
Output (completion)
5.6Credits / M
Cache read0.28 Credits / MCache write (general)1.75 Credits / M
8.0 t/s30% off

Qwen3.8-FlashText

Qwen · 1M context
qwen3.8-flash
Input (prompt)
0.56Credits / M
Output (completion)
1.89Credits / M
Cache read0.07 Credits / MCache write (general)0.98 Credits / M
11/2/2026, 6:38:47 AM95.6%
7.0 t/sLatency 2.3s30% off

Qwen3.8 MaxText

Qwen · 1M context
qwen3.8-max
Input (prompt)
8.4Credits / M
Output (completion)
25.2Credits / M
Cache read1.05 Credits / MCache write (general)10.5 Credits / M
5.4 t/s30% off