Catalog

Model catalog and prices

Every model on one key and one balance. Compare price, context and speed, copy the ID and start coding.

models in the catalog: 69
providers: 13
cheapest input per 1M · Qwen3 Embedding 8B: $0.02
largest context, tokens · GPT-5.4: 1.1M

Quick picks

BAAI · Text models
No readings
Context
8K
Latency
—
Input$0.02
Output$0.00
per 1M tokens
Compare BGE M3 EmbeddingModel page
Qwen · Text models
No readings
Context
33K
Latency
—
Input$0.02
Output$0.00
per 1M tokens
Compare Qwen3 Embedding 8BModel page
DeepSeek · Text models
No readings
Context
1M
Latency
≈ 5 s
Input$0.03
Output$0.07
per 1M tokens
Compare DeepSeek V4 FlashModel page
DeepSeek · Text models
Healthy
Understands images
Context
1M
Latency
≈ 24 s
Input$0.03
Output$0.15
per 1M tokens
Compare DeepSeek V4.1 FlashModel page
Xiaomi · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.03
Output$0.09
per 1M tokens
Compare Mimo V2.5Model page
Qwen · Text models
No readings
Context
33K
Latency
—
Input$0.04
Output$0.00
per 1M tokens
Compare Qwen3 Embedding 4BModel page
OpenAI · Text models
No readings
Context
8K
Latency
—
Input$0.04
Output$0.00
per 1M tokens
Compare Text Embedding 3 SmallModel page
Z-AI · Text models
No readings
Understands images
Context
1M
Latency
≈ 7.3 s
Input$0.06
Output$0.25
per 1M tokens
Compare GLM-5.3 FlashModel page
Google · Text models
No readings
Understands images
Context
1M
Latency
≈ 3.5 s
Input$0.06
Output$0.49
per 1M tokens
Compare Gemini 3.1 Flash LiteModel page
Moonshot · Text models
No readings
Context
256K
Latency
—
Input$0.07
Output$0.30
per 1M tokens
Compare Kimi K2.6Model page
Google · Text models
Healthy
Understands images
Context
1M
Latency
≈ 30 s
Input$0.08
Output$0.34
per 1M tokens
Compare Gemini 3.8 FlashModel page
MiniMax · Text models
No readings
Understands images
Context
512K
Latency
—
Input$0.09
Output$0.39
per 1M tokens
Compare MiniMax M3Model page
Moonshot · Text models
No readings
Context
256K
Latency
—
Input$0.09
Output$0.41
per 1M tokens
Compare Kimi K2.7 CodeModel page
Xiaomi · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.11
Output$0.28
per 1M tokens
Compare Mimo V2.5 ProModel page
Qwen · Text models
No readings
Context
1M
Latency
—
Input$0.11
Output$0.35
per 1M tokens
Compare Qwen3.7 PlusModel page
OpenAI · Text models
Healthy
Understands images
Context
272K
Latency
≈ 65 s
Input$0.11
Output$0.63
per 1M tokens
Compare GPT-5.4 MiniModel page
Moonshot · Text models
No readings
Context
256K
Latency
—
Input$0.13
Output$0.89
per 1M tokens
Compare Kimi K2.7 Code HSModel page
Anthropic · Text models
Healthy
Understands images
Context
200K
Latency
≈ 29 s
Input$0.14
Output$0.78
per 1M tokens
Compare Claude Haiku 4.5Model page
OpenAI · Text models
No readings
Understands images
Context
372K
Latency
—
Input$0.14
Output$0.88
per 1M tokens
Compare GPT-5.6 LunaModel page
xAI · Text models
Healthy
Understands images
Context
256K
Latency
≈ 69 s
Input$0.15
Output$0.43
per 1M tokens
Compare Grok 4.6Model page
Moonshot · Text models
No readings
Understands images
Context
262K
Latency
—
Input$0.16
Output$0.77
per 1M tokens
Compare Kimi K2.5Model page
Google · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.16
Output$0.59
per 1M tokens
Compare Gemini 3 FlashModel page
xAI · Text models
No readings
Understands images
Context
256K
Latency
—
Input$0.18
Output$0.39
per 1M tokens
Compare Grok Build 0.1Model page
Qwen · Text models
No readings
Context
1M
Latency
—
Input$0.20
Output$0.56
per 1M tokens
Compare Qwen3.7 MaxModel page
DeepSeek · Text models
No readings
Context
1M
Latency
—
Input$0.21
Output$0.78
per 1M tokens
Compare DeepSeek V4 Pro 0813Model page
Qwen · Text models
No readings
Context
1M
Latency
—
Input$0.22
Output$0.45
per 1M tokens
Compare Qwen 3.5 FlashModel page
Google · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.24
Output$1.49
per 1M tokens
Compare Gemini 3.6 FlashModel page
Z-AI · Text models
No readings
Context
1M
Latency
—
Input$0.25
Output$0.97
per 1M tokens
Compare GLM-5.2Model page
Z-AI · Text models
No readings
Understands images
Context
200K
Latency
—
Input$0.27
Output$0.87
per 1M tokens
Compare GLM-5.1Model page
Anthropic · Text models
Unstable
Understands images
Context
324K
Latency
≈ 53 s
Input$0.28
Output$1.23
per 1M tokens
Compare Claude Sonnet 5Model page
OpenAI · Text models
Healthy
Context
1.1M
Latency
≈ 21 s
Input$0.28
Output$1.97
per 1M tokens
Compare GPT-5.4Model page
OpenAI · Text models
No readings
Understands images
Context
372K
Latency
—
Input$0.29
Output$1.98
per 1M tokens
Compare GPT-5.6 TerraModel page
OpenAI · Text models
No readings
Understands images
Context
400K
Latency
—
Input$0.29
Output$2.79
per 1M tokens
Compare GPT-5.3 CodexModel page
Qwen · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.32
Output$1.19
per 1M tokens
Compare Qwen3.8 MaxModel page
xAI · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.37
Output$0.74
per 1M tokens
Compare Grok 4.3Model page
DeepSeek · Text models
No readings
Context
1M
Latency
—
Input$0.38
Output$0.84
per 1M tokens
Compare DeepSeek V4 ProModel page
Anthropic · Text models
No readings
Understands images
Context
200K
Latency
—
Input$0.38
Output$1.97
per 1M tokens
Compare Claude Sonnet 4.5Model page
Anthropic · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.38
Output$1.97
per 1M tokens
Compare Claude Sonnet 4.6Model page
xAI · Text models
No readings
Understands images
Context
256K
Latency
—
Input$0.38
Output$0.98
per 1M tokens
Compare Grok 4.5Model page
Qwen · Text models
No readings
Context
1M
Latency
—
Input$0.45
Output$1.82
per 1M tokens
Compare Qwen 3.8 Max PreviewModel page
Anthropic · Text models
No readings
Understands images
Context
200K
Latency
—
Input$0.47
Output$2.64
per 1M tokens
Compare Claude Opus 4.8Model page
Anthropic · Text models
Healthy
Understands images
Context
1M
Latency
≈ 47 s
Input$0.47
Output$2.64
per 1M tokens
Compare Claude Opus 5Model page
Google · Text models
Healthy
Context
1M
Latency
≈ 24 s
Input$0.51
Output$2.10
per 1M tokens
Compare Gemini 4 ArgonModel page
Moonshot · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.59
Output$1.77
per 1M tokens
Compare Kimi K3Model page
Moonshot · Text models
No readings
Context
200K
Latency
—
Input$0.59
Output$1.77
per 1M tokens
Compare Kimi K3.1 ProModel page
Anthropic · Text models
No readings
Understands images
Context
200K
Latency
—
Input$0.64
Output$2.97
per 1M tokens
Compare Claude Opus 4.5Model page
Anthropic · Text models
No readings
Understands images
Context
200K
Latency
—
Input$0.64
Output$2.97
per 1M tokens
Compare Claude Opus 4.6Model page
Anthropic · Text models
No readings
Understands images
Context
1M
Latency
≈ 14 s
Input$0.64
Output$2.97
per 1M tokens
Compare Claude Opus 4.7Model page
OpenAI · Text models
Healthy
Understands images
Context
258K
Latency
≈ 32 s
Input$0.64
Output$3.46
per 1M tokens
Compare GPT-5.5Model page
OpenAI · Text models
No readings
Understands images
Context
786K
Latency
≈ 4.6 s
Input$0.67
Output$3.94
per 1M tokens
Compare GPT-5.6 SolModel page
OpenAI · Text models
Healthy
Understands images
Context
250K
Latency
≈ 60 s
Input$0.67
Output$2.22
per 1M tokens
Compare GPT-6 AstraModel page
Google · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.78
Output$2.98
per 1M tokens
Compare Gemini 2.5 ProModel page
Z-AI · Text models
No readings
Understands images
Context
1M
Latency
—
Input$0.84
Output$3.23
per 1M tokens
Compare GLM-5.3Model page
Moonshot · Text models
No readings
Context
200K
Latency
—
Input$0.85
Output$1.77
per 1M tokens
Compare Kimi K3.1 Pro HSModel page
Google · Text models
No readings
Understands images
Context
1M
Latency
≈ 4.5 s
Input$0.94
Output$2.89
per 1M tokens
Compare Gemini 3.1 ProModel page
Google · Text models
No readings
Understands images
Context
1M
Latency
≈ 2.9 s
Input$0.97
Output$2.17
per 1M tokens
Compare Gemini 3.7 FlashModel page
OpenAI · Pictures
No readings
Image editing
Context
—
Latency
≈ 66 s
Input$1.42
Output$8.55
per 1M tokens
Compare GPT Image 2Model page
Anthropic · Text models
No readings
Understands images
Context
1M
Latency
≈ 6.5 s
Input$2.25
Output$10.33
per 1M tokens
Compare Claude Fable 5.1Model page
Anthropic · Text models
No readings
Understands images
Context
1M
Latency
≈ 13 s
Input$2.26
Output$11.49
per 1M tokens
Compare Claude Fable 5Model page
Anthropic · Text models
No readings
Understands images
Context
—
Latency
—
Input$2.29
Output$11.49
per 1M tokens
Compare Claude Fable 5 experimental compressed contextModel page
Anthropic · Text models
Healthy
Context
—
Latency
≈ 35 s
Input$4.40
Output$22.00
per 1M tokens
Compare Claude Opus 5.5Model page
Google · Pictures
No readings
Image editing
Unit
per unit
Latency
≈ 32 s
Price$0.01
per unit
Compare Gemini 3.1 Flash ImageModel page
OpenAI · Pictures
No readings
Unit
per unit
Latency
≈ 85 s
Price$0.08
per unit
Compare GPT Image 2.5 FlareModel page
OpenAI · Pictures
No readings
Unit
per unit
Latency
—
Price$0.08
per unit
Compare GPT Image 2.5 SunburstModel page
Alibaba · Video
No readings
Unit
per sec.
Latency
—
Price$0.11
per sec.
Compare Wan 2.6Model page
Google · Video
No readings
Unit
per sec.
Latency
—
Price$0.13
per sec.
Compare Veo 3.1 FastModel page
ByteDance · Video
No readings
Unit
per sec.
Latency
—
Price$0.23
per sec.
Compare Seedance 2.0 FastModel page
Google · Video
No readings
Unit
per sec.
Latency
—
Price$0.27
per sec.
Compare Veo 3.1Model page
ByteDance · Video
No readings
Unit
per sec.
Latency
—
Price$0.29
per sec.
Compare Seedance 2.0Model page

Accounting inside the service is in USD; EUR prices are recalculated at the current rate and may change.

Price bars use a log scale relative to the most expensive price in the catalog; media models are compared with the priciest model of the same unit.

Status reflects requests over the last 6 hours; latency is the average response time over 48 hours. See the Status page for details.

BGE M3 Embedding

Qwen3 Embedding 8B

DeepSeek V4 Flash

DeepSeek V4.1 Flash

Mimo V2.5

Qwen3 Embedding 4B

Text Embedding 3 Small

GLM-5.3 Flash

Gemini 3.1 Flash Lite

Kimi K2.6

Gemini 3.8 Flash

MiniMax M3

Kimi K2.7 Code

Mimo V2.5 Pro

Qwen3.7 Plus

GPT-5.4 Mini

Kimi K2.7 Code HS

Claude Haiku 4.5

GPT-5.6 Luna

Grok 4.6

Kimi K2.5

Gemini 3 Flash

Grok Build 0.1

Qwen3.7 Max

DeepSeek V4 Pro 0813

Qwen 3.5 Flash

Gemini 3.6 Flash

GLM-5.2

GLM-5.1

Claude Sonnet 5

GPT-5.4

GPT-5.6 Terra

GPT-5.3 Codex

Qwen3.8 Max

Grok 4.3

DeepSeek V4 Pro

Claude Sonnet 4.5

Claude Sonnet 4.6

Grok 4.5

Qwen 3.8 Max Preview

Claude Opus 4.8

Claude Opus 5

Gemini 4 Argon

Kimi K3

Kimi K3.1 Pro

Claude Opus 4.5

Claude Opus 4.6

Claude Opus 4.7

GPT-5.5

GPT-5.6 Sol

GPT-6 Astra

Gemini 2.5 Pro

GLM-5.3

Kimi K3.1 Pro HS

Gemini 3.1 Pro

Gemini 3.7 Flash

GPT Image 2

Claude Fable 5.1

Claude Fable 5

Claude Fable 5 experimental compressed context

Claude Opus 5.5

Gemini 3.1 Flash Image

GPT Image 2.5 Flare

GPT Image 2.5 Sunburst

Wan 2.6

Veo 3.1 Fast

Seedance 2.0 Fast

Veo 3.1

Seedance 2.0