Models

Prices in USD in the unit shown on each row (per million tokens for text models). Uptime is the share of successful API responses over the last 30 days. A price range means the price varies by provider, time of day or prompt length.

OpenAPI

Tencent Hy4viaTencent Cloud TokenHub
Input
$0.438
Output
$1.314
Unit
per 1M tokens
Cache read
$0.0219
Context
1M
Max output
64K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Tencent's Hy4 flagship reasoning model with native vision for agentic coding, computer use, finance, and research workflows.
viaTencent Cloud TokenHub
OhMyGPT MockviaOhMyGPT
Input
Free
Output
Free
Unit
per 1M tokens
Cache read
Free
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Free deterministic test model answered by the gateway itself. Replies with fixed text, or calls the first declared tool, on every protocol, streaming or not. Use it to verify an integration before switching to a real model.
viaOhMyGPT
Kling Video 4.0Video generationviaTencent Cloud TokenHub
Video
$1.46per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageReturnsVideo
Kuaishou's Kling 4.0 video model for clips up to 30 seconds from text, frames, or reference images.
viaTencent Cloud TokenHub
GPT-6.1 TerraviaAzure AI Foundry, OpenAI
Input
from $0.90list $1.00
Output
from $4.50list $5.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.045list $0.05
Context
1.1M
Max output
128K
Capability
168
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's fast, efficient GPT-6.1 model for visual reasoning, precise computer use, and clear, natural writing.
viaAzure AI Foundry, OpenAI
Kimi K3.1 ProviaMoonshot AI (Kimi), Tencent Cloud TokenHub
Input
$2.0878
Output
$10.9208
Unit
per 1M tokens
Cache read
$0.20878
Context
1M
Max output
1M
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideo
Moonshot AI's flagship 3T-class open-weight model with 1M context, strong coding, 3D creation, and financial research.
viaMoonshot AI (Kimi), Tencent Cloud TokenHub
Kimi K3.1 Pro HighSpeedviaMoonshot AI (Kimi), Tencent Cloud TokenHub
Input
$4.1756
Output
$21.8416
Unit
per 1M tokens
Cache read
$0.20878
Context
1M
Max output
1M
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideo
Kimi K3.1 Pro served at 2-3x output speed for latency-sensitive workloads.
viaMoonshot AI (Kimi), Tencent Cloud TokenHub
DeepSeek V4.1 Flash 1017viaByteDance (Volcano Engine), Fireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, DeepSeek, Alibaba Cloud (Model Studio Intl), Cloudflare Workers AI+4
Input
from $0.015list $0.30
Output
from $0.06list $1.20
Discount
-95%
Unit
per 1M tokens
Cache read
from $0.0003list $0.006
Context
1M
Max output
384K
Capability
159
First token
—
30-day uptime
—
Providers
lowest of 8 providers
AcceptsTextImage
DeepSeek V4.1 Flash 1017: natively multimodal vision understanding, with stronger coding and agentic performance than the 0910 release, 1M context and 384K max output.
viaByteDance (Volcano Engine), Fireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, DeepSeek, Alibaba Cloud (Model Studio Intl), Cloudflare Workers AI+4
NVIDIA Nemotron 3.5 Super VLviaTogether AI
Input
$0.165
Output
$0.55
Unit
per 1M tokens
Cache read
$0.022
Context
1M
Max output
262K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
NVIDIA's open 120B vision-language MoE for agentic tool use, coding, and document understanding.
viaTogether AI
Gemini 4 ArgonviaGoogle (Gemini), Google Vertex AI
Input
$1.80list $2.00
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.09list $0.10
Context
1M
Max output
66K
Capability
166
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long decode up to 1M tokens.
viaGoogle (Gemini), Google Vertex AI
Claude Haiku 5.5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $0.11
Output
from $0.55
Unit
per 1M tokens
Cache read
from $0.011
Context
1M
Max output
128K
Capability
160
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's fastest and most affordable small model for high-volume, latency-sensitive work such as classification, routing, extraction, and subagents.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Gemini Nano Banana 2.1viaGoogle (Gemini), Google Vertex AI
Input
$1.35list $1.50
Output
$6.75list $7.50
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.135list $0.15
Context
131K
Max output
33K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideoPDFReturnsTextImage
An update to Nano Banana 2 for image generation and conversational editing, with improved visual quality, multi-turn character consistency, accurate text rendering, and search-grounded generation at 1K, 2K, and 4K.
viaGoogle (Gemini), Google Vertex AI
Mistral Large 4viaMistral AI
Input
$0.77
Output
$2.31
Unit
per 1M tokens
Cache read
$0.077
Context
1M
Max output
262K
Capability
151
First token
—
30-day uptime
—
AcceptsTextImagePDF
Mistral AI's 1.05T-parameter multimodal MoE for reasoning, coding, and agentic work.
viaMistral AI
Embed v5.0 FastEmbeddingsviaCohere
Embedding input
$0.088per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Faster, lower-cost Embed 5 model sharing the Pro embedding space, with 128K context and up to 2048-dim vectors.
viaCohere
Embed v5.0 ProEmbeddingsviaCohere
Embedding input
$0.132per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere's highest-quality Embed 5 model for multilingual enterprise retrieval, with 128K context and up to 2048-dim vectors.
viaCohere
GPT-6.1 SolviaAzure AI Foundry, OpenAI
Input
from $1.80list $2.00
Output
from $9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.09list $0.10
Context
1.1M
Max output
128K
Capability
168
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's upgraded GPT-6 Sol with near-Astra performance for complex coding, computer use, and professional work.
viaAzure AI Foundry, OpenAI
Claude Sonnet 5.5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $2.20
Output
from $11.00
Unit
per 1M tokens
Cache read
from $0.11
Context
1M
Max output
128K
Capability
167
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's Claude Sonnet 5.5 for everyday coding, agentic tasks, and polished documents, faster than Sonnet 5 at the same price.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
MiniMax M3.1 FlashviaMiniMax, Tencent Cloud TokenHub, Together AI
Input
from $0.1606
Output
from $0.6424
Unit
per 1M tokens
Cache read
from $0.01606
Context
1M
Max output
524K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImageVideo
MiniMax's frontier multimodal coding model with a 1M context window and tunable thinking depth.
viaMiniMax, Tencent Cloud TokenHub, Together AI
Claude Opus 5.5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $4.40
Output
from $22.00
Unit
per 1M tokens
Cache read
from $0.22
Context
1M
Max output
128K
Capability
168
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's Claude Opus 5.5 for long-running agentic coding and knowledge work, priced below Opus 5 with adaptive thinking always on.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Ember-1viaFireworks AI
Input
$3.00
Output
$15.00
Unit
per 1M tokens
Cache read
$0.30
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Fireworks' specialized model built on Kimi K3 with shorter reasoning traces for efficient agentic workloads.
viaFireworks AI
Gemini 3.8 Flash TTSviaGoogle (Gemini), Google Vertex AI
Input
$0.45list $0.50
Output
$8.10list $9.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
8K
Max output
16K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextReturnsAudio
Google's flagship text-to-speech model for studio-grade voice fidelity, expressive acting, regional accents, and stable long-form multi-speaker audio.
viaGoogle (Gemini), Google Vertex AI
Gemini 3.8 Flash-Lite TTSviaGoogle (Gemini), Google Vertex AI
Input
$0.45list $0.50
Output
$5.40list $6.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
8K
Max output
16K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextReturnsAudio
Google's fast, cost-efficient text-to-speech model for high-volume and real-time single- and multi-speaker speech.
viaGoogle (Gemini), Google Vertex AI
GPT-6 LunaviaAzure AI Foundry, OpenAI
Input
from $0.09list $0.10
Output
from $0.45list $0.50
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.009list $0.01
Context
1.1M
Max output
128K
Capability
157
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's cost-efficient GPT-6 model for high-volume workloads such as extraction, summarization, and routing.
viaAzure AI Foundry, OpenAI
GPT-6 SolviaAzure AI Foundry, OpenAI
Input
from $1.80list $2.00
Output
from $9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.18list $0.20
Context
1.1M
Max output
128K
Capability
164
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's frontier GPT-6 model for enterprise agents, coding, writing, and complex knowledge work.
viaAzure AI Foundry, OpenAI
MiMo-V2.6-FlashviaTencent Cloud TokenHub
Input
$0.1606
Output
$0.3212
Unit
per 1M tokens
Cache read
$0.003212
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudio
Xiaomi's efficient omni-modal reasoning model (309B total, 15B active) for high-volume coding and agent workflows.
viaTencent Cloud TokenHub
MiMo-V2.6-ProviaTencent Cloud TokenHub
Input
$0.4818
Output
$0.9636
Unit
per 1M tokens
Cache read
$0.004016
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudio
Xiaomi's flagship omni-modal reasoning model (1.02T total, 42B active) for long-horizon agents, coding, and research.
viaTencent Cloud TokenHub
Step 5 PreviewviaTencent Cloud TokenHub
Input
$1.1242
Output
$3.212
Unit
per 1M tokens
Cache read
$0.056212
Context
1M
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
StepFun's flagship 600B MoE model (27B active) for agentic coding and professional knowledge work, with 1M context and vision input.
viaTencent Cloud TokenHub
GLM-5.3-FlashXviaZhipu AI (ChatGLM), Tencent Cloud TokenHub
Input
$0.3212
Output
$1.1242
Unit
per 1M tokens
Cache read
$0.091544
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideoPDF
High-speed serving option of GLM-5.3-Flash for coding and agent workflows.
viaZhipu AI (ChatGLM), Tencent Cloud TokenHub
Qwen3.8 Omni FlashviaAlibaba Cloud (Model Studio Intl)
Input
$0.113
Output
$0.382
Unit
per 1M tokens
Cache read
$0.014
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudio
Qwen3.8 omni-modal model for audio and video understanding with text output.
viaAlibaba Cloud (Model Studio Intl)
Doubao Seed 2.1 Lite (260915)viaByteDance (Volcano Engine)
Input
$0.1168
Output
$0.3942
Unit
per 1M tokens
Cache read
$0.02336
Context
1M
Max output
256K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
A lower-cost Doubao Seed 2.1 variant for everyday multimodal workloads.
viaByteDance (Volcano Engine)
Doubao Seed 2.1 Pro (260915)viaByteDance (Volcano Engine)
Input
$0.876
Output
$4.38
Unit
per 1M tokens
Cache read
$0.1752
Context
1M
Max output
256K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
ByteDance's flagship Doubao Seed 2.1 model with 1M context for coding and agent workloads.
viaByteDance (Volcano Engine)
Gemini 3.8 LiveviaGoogle (Gemini)
Input
$0.675list $0.75
Output
$4.05list $4.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.675list $0.75
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudioReturnsTextAudio
Google Gemini 3.8 real-time bidirectional Live API model for low-latency voice agents. Supports text, image, and audio input with text and audio output.
viaGoogle (Gemini)
Gemini 3.8 Live Extended ThinkingviaGoogle (Gemini)
Input
$0.675list $0.75
Output
$4.05list $4.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.675list $0.75
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudioReturnsTextAudio
Google Gemini 3.8 Live with background reasoning for real-time voice agents that need deeper thinking. Supports text, image, and audio input with text and audio output.
viaGoogle (Gemini)
JevDecisionviaTypeSafe AI
Input
$0.042per 1M tokens
Context
64K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
TypeSafe System One decision model. Evaluates a state against typed questions and returns typed answers (noul probability / choice / score / box) with calibrated confidence; it does not generate text. Image assets (and box questions) require the TypeSafe-Danger-Zone-Images: true header.
viaTypeSafe AI
Kimi K2.8 PreviewviaTencent Cloud TokenHub
Input
$1.0439
Output
$4.3362
Unit
per 1M tokens
Cache read
$0.27302
Context
1M
Max output
1M
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Moonshot AI's K2.8 preview for coding and agent work, close to Kimi K3 with more efficient thinking and 1M context.
viaTencent Cloud TokenHub
DeepSeek V4.1 FlashviaByteDance (Volcano Engine), Fireworks AI, Together AI, Alibaba Cloud (Model Studio Intl)
Input
from $0.073list $0.146-50%
Output
from $0.292list $0.584-50%
Unit
per 1M tokens
Cache read
from $0.00292
Context
1M
Max output
384K
Capability
156
First token
—
30-day uptime
—
Providers
lowest of 4 providers
AcceptsTextImage
DeepSeek V4.1 Flash: natively multimodal vision understanding with 1M context and 384K max output.
viaByteDance (Volcano Engine), Fireworks AI, Together AI, Alibaba Cloud (Model Studio Intl)
GPT Image 2.5 FlareImage generationviaAzure AI Foundry, OpenAI
Image output
$27.00list $30.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageReturnsImage
OpenAI's fastest image model for high-quality everyday generation and editing, with text and image inputs.
viaAzure AI Foundry, OpenAI
GPT Image 2.5 SunburstImage generationviaAzure AI Foundry, OpenAI
Image output
$27.00list $30.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageReturnsImage
OpenAI's most capable image model for generation and editing where editing precision matters most, with text and image inputs.
viaAzure AI Foundry, OpenAI
GPT-6 AstraviaAzure AI Foundry, OpenAI
Input
from $9.00list $10.00
Output
from $45.00list $50.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.90list $1.00
Context
1.1M
Max output
128K
Capability
169
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use, research, and document creation.
viaAzure AI Foundry, OpenAI
Gemini 3.8 FlashviaGoogle (Gemini), Google Vertex AI
Input
$0.675list $0.75
Output
$3.375list $3.75
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
1M
Max output
64K
Capability
158
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Google's workhorse model for coding and agents, with sharper multi-turn coding, rapid refactoring, code synthesis, and tighter tool-execution logic.
viaGoogle (Gemini), Google Vertex AI
Qwen3.8 Max 0902viaAlibaba Cloud (Model Studio Intl)
Input
$1.65
Output
$4.951
Unit
per 1M tokens
Cache read
$0.206
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Upgraded Qwen3.8 Max snapshot with stronger coding, multi-tool agent work, and vision understanding.
viaAlibaba Cloud (Model Studio Intl)
Claude Fable 5.1viaAnthropic, Amazon Bedrock
Input
from $11.00
Output
from $55.00
Unit
per 1M tokens
Cache read
from $0.275
Context
1M
Max output
128K
Capability
166
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDF
Claude Fable 5.1 extends Claude Fable 5 with stronger long-running agentic coding, knowledge work, and research. Same $10/$50 rates with cache reads at a quarter of the cost.
viaAnthropic, Amazon Bedrock
Tencent Hy4 PreviewviaTencent Cloud TokenHub
Input
$0.876
Output
$2.628
Unit
per 1M tokens
Cache read
$0.0438
Context
1M
Max output
64K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy4 preview reasoning model served by TokenHub for coding agents, complex tool calls, and multi-step agentic workflows.
viaTencent Cloud TokenHub
Gemini 3.5 TranscribeviaGoogle (Gemini), Google Vertex AI
Input
$1.80list $2.00
Output
$10.80list $12.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.80list $2.00
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsAudio
Google Gemini 3.5 speech-to-text for audio files up to one hour, with language detection, speaker diarization, word-level timestamps, and custom vocabulary.
viaGoogle (Gemini), Google Vertex AI
Gemini 3.5 Transcribe LiveviaGoogle (Gemini)
Input
$3.15list $3.50
Output
$18.90list $21.00
Discount
-10%
Unit
per 1M tokens
Cache read
$3.15list $3.50
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsAudio
Google Gemini 3.5 low-latency speech-to-text over the Live API for bidirectional streaming audio transcription.
viaGoogle (Gemini)
GLM-5.3-FlashviaZhipu AI (ChatGLM), Fireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, Cloudflare Workers AI+2
Input
from $0.0075list $0.15
Output
from $0.025list $0.50
Discount
-95%
Unit
per 1M tokens
Cache read
from $0.0015list $0.03
Context
1M
Max output
131K
Capability
153
First token
—
30-day uptime
—
Providers
lowest of 6 providers
AcceptsTextImageVideoPDF
Zhipu's first natively multimodal GLM-5 model (320B/18B MoE) with 1M context and visual coding capabilities.
viaZhipu AI (ChatGLM), Fireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, Cloudflare Workers AI+2
Grok Imagine Video 1.5 LiteVideo generationviaxAI
Video
$0.022per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsVideo
xAI's lowest-cost video model for simple text-to-video clips with audio.
viaxAI
Qwen3.8 FlashviaAlibaba Cloud (Model Studio Intl)
Input
$0.113
Output
$0.382
Unit
per 1M tokens
Cache read
$0.014
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Fast, low-cost Qwen3.8 multimodal model with 1M context for coding, agents, and visual understanding.
viaAlibaba Cloud (Model Studio Intl)
Wan 3.0 Video PrimeVideo generationviaAlibaba Cloud (Model Studio Intl)
Video
$0.0636per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
A faster Wan 3.0 video model with the same multimodal inputs and native audio.
viaAlibaba Cloud (Model Studio Intl)
GLM-5.3viaFireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl), Cloudflare Workers AI, Amazon Bedrock+3
Input
from $0.07list $1.40
Output
from $0.22list $4.40
Discount
-95%
Unit
per 1M tokens
Cache read
from $0.013list $0.26
Context
1M
Max output
131K
Capability
156
First token
—
30-day uptime
—
Providers
lowest of 7 providers
AcceptsText
Z.ai's latest flagship reasoning model with a 1M-token context window and controllable thinking length.
viaFireworks AI, Mistral AI, Tencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl), Cloudflare Workers AI, Amazon Bedrock+3
Qwen3.8 27BviaCerebras, Groq, Cloudflare Workers AI
Input
from $0.495
Output
from $1.639
Unit
per 1M tokens
Cache read
from $0.055
Context
262K
Max output
131K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImage
Qwen3.8 27B open-weight dense vision-language model with default-on thinking for coding and agentic tasks.
viaCerebras, Groq, Cloudflare Workers AI
Gemini 3.7 FlashviaGoogle Vertex AI
Input
$0.675list $0.75
Output
$3.375list $3.75
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
1M
Max output
64K
Capability
158
First token
—
30-day uptime
—
AcceptsTextImageAudioVideoPDF
Google's most intelligent workhorse model for coding and agentic workflows.
viaGoogle Vertex AI
Wan 3.0 VideoVideo generationviaAlibaba Cloud (Model Studio Intl)
Video
$0.041256per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
Alibaba's all-in-one Wan 3.0 video model with native audio, first and last frame control, and multimodal reference up to 30 seconds.
viaAlibaba Cloud (Model Studio Intl)
DeepSeek V4 Flash 0731viaAlibaba Cloud (Model Studio Intl)
Input
$0.1104list $0.138
Output
$0.22list $0.275
Discount
-20%
Unit
per 1M tokens
Cache read
$0.0224list $0.028
Context
1M
Max output
384K
Capability
155
First token
—
30-day uptime
—
AcceptsText
DeepSeek V4 Flash 0731 weight snapshot with 1M context and 384K max output.
viaAlibaba Cloud (Model Studio Intl)
MiniMax H3Video generationviaMiniMax
Video
$0.073per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
MiniMax's H3 video model for high-quality text-to-video, first and last frame, and multimodal reference clips up to 2K with native audio.
viaMiniMax
GPT TranscribeSpeech to textviaOpenAI
Transcription
$0.000068list $0.000076-11%per second
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsAudio
Speech-to-text model for completed audio files, with context, keyword hints, and multiple language hints for domain terms and code-switching.
viaOpenAI
Claude Opus 5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $5.50
Output
from $27.50
Unit
per 1M tokens
Cache read
from $0.55
Context
1M
Max output
128K
Capability
164
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's flagship Opus model with enhanced agentic capabilities, priced identically to Opus 4.8.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Opus 5 (Reseller)viaReseller (managed pool)
Input
$1.50
Output
$7.50
Unit
per 1M tokens
Cache read
$0.15
Context
200K
Max output
64K
Capability
164
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Opus 5 via third-party reseller channels. Same model family as anthropic/claude-opus-5, served from managed pools with 200K context.
viaReseller (managed pool)
Gemini 3.5 Flash-LiteviaGoogle (Gemini), Google Vertex AI
Input
$0.27list $0.30
Output
$2.25list $2.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.027list $0.03
Context
1M
Max output
64K
Capability
145
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Google's high-throughput Gemini 3.5 model for agentic search, document processing, and translation.
viaGoogle (Gemini), Google Vertex AI
Gemini 3.6 FlashviaGoogle (Gemini), Google Vertex AI
Input
$0.675list $0.75
Output
$3.375list $3.75
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
1M
Max output
64K
Capability
155
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Google's multimodal workhorse model for coding, knowledge work, and agentic workflows.
viaGoogle (Gemini), Google Vertex AI
Kimi K3viaFireworks AI, Moonshot AI (Kimi), Tencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl), Amazon Bedrock+2
Input
from $2.827
Output
from $14.133
Unit
per 1M tokens
Cache read
from $0.283
Context
1M
Max output
1M
Capability
158
First token
—
30-day uptime
—
Providers
lowest of 6 providers
AcceptsTextImageVideo
Moonshot AI's flagship native multimodal model for long-horizon coding, knowledge work, and deep reasoning.
viaFireworks AI, Moonshot AI (Kimi), Tencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl), Amazon Bedrock+2
GPT-5.6viaAzure AI Foundry, OpenAI
Input
from $3.60list $4.00
Output
from $18.00list $20.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.36list $0.40
Context
1.1M
Max output
128K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's GPT-5.6 alias, routing to GPT-5.6 Sol for frontier reasoning, coding, and production workflows.
viaAzure AI Foundry, OpenAI
GPT-5.6 LunaviaAzure AI Foundry, OpenAI
Input
from $0.18list $0.20
Output
from $1.08list $1.20
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.018list $0.02
Context
1.1M
Max output
128K
Capability
157
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
A cost-efficient GPT-5.6 model optimized for high-volume reasoning and tool-use workloads.
viaAzure AI Foundry, OpenAI
GPT-5.6 SolviaAzure AI Foundry, OpenAI
Input
from $3.60list $4.00
Output
from $18.00list $20.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.36list $0.40
Context
1.1M
Max output
128K
Capability
163
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
The frontier GPT-5.6 model for complex reasoning, coding, tool use, and demanding production workflows.
viaAzure AI Foundry, OpenAI
GPT-5.6 Sol (Reseller)viaReseller (managed pool)
Input
from $2.50
Output
from $15.00
Unit
per 1M tokens
Cache read
—
Context
1.1M
Max output
128K
Capability
163
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.6 Sol via third-party reseller channels (Responses API, 272K tiered billing).
viaReseller (managed pool)
GPT-5.6 TerraviaAzure AI Foundry, OpenAI
Input
from $1.80list $2.00
Output
from $10.80list $12.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.18list $0.20
Context
1.1M
Max output
128K
Capability
160
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
A balanced GPT-5.6 model for strong reasoning and coding performance at a lower price point.
viaAzure AI Foundry, OpenAI
GPT-5.6 Terra (Reseller)viaReseller (managed pool)
Input
from $1.00
Output
from $6.00
Unit
per 1M tokens
Cache read
—
Context
1.1M
Max output
128K
Capability
160
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.6 Terra via third-party reseller channels (Responses API, 272K tiered billing).
viaReseller (managed pool)
GPT Realtime 2.1viaOpenAI
Input
$4.40
Output
$26.40
Unit
per 1M tokens
Cache read
$0.44
Context
128K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
OpenAI's current realtime speech model, responding to audio, image, and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
GPT Realtime 2.1 MiniviaOpenAI
Input
$0.66
Output
$2.64
Unit
per 1M tokens
Cache read
$0.066
Context
128K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
A cost-efficient version of GPT Realtime 2.1, responding to audio, image, and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
Claude Sonnet 5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $2.20
Output
from $11.00
Unit
per 1M tokens
Cache read
from $0.22
Context
1M
Max output
128K
Capability
157
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's Sonnet model for coding, agents, and complex reasoning with a 1M-token context window.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Sonnet 5 (Reseller)viaReseller (managed pool)
Input
$0.60
Output
$3.00
Unit
per 1M tokens
Cache read
$0.06
Context
200K
Max output
64K
Capability
157
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Sonnet 5 via third-party reseller channels with 200K context.
viaReseller (managed pool)
Doubao Seedance 2.5 (260628)Video generationviaByteDance (Volcano Engine)
Video
$10.22per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
ByteDance's Seedance 2.5 video model for clips up to 30 seconds with native audio and multimodal reference.
viaByteDance (Volcano Engine)
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)viaGoogle (Gemini), Google Vertex AI
Input
$0.225list $0.25
Output
$1.35list $1.50
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.0225list $0.025
Context
66K
Max output
4K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideoPDFReturnsTextImage
Google's fastest and most cost-efficient image generation and editing model, built for ultra-low latency.
viaGoogle (Gemini), Google Vertex AI
HappyHorse 1.1 Image-to-VideoVideo generationviaAlibaba Cloud (Model Studio Intl)
Video
$0.061888per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageReturnsVideo
Alibaba's HappyHorse 1.1 model that animates a first-frame image into a video with native audio.
viaAlibaba Cloud (Model Studio Intl)
HappyHorse 1.1 Reference-to-VideoVideo generationviaAlibaba Cloud (Model Studio Intl)
Video
$0.061888per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageReturnsVideo
Alibaba's HappyHorse 1.1 model that generates a video from one to nine reference images with native audio.
viaAlibaba Cloud (Model Studio Intl)
HappyHorse 1.1 Text-to-VideoVideo generationviaAlibaba Cloud (Model Studio Intl)
Video
$0.061888per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsVideo
Alibaba's HappyHorse 1.1 text-to-video model with cinematic shot control and native audio.
viaAlibaba Cloud (Model Studio Intl)
GLM-5.2viaTencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl)
Input
from $0.66list $1.10
Output
from $2.3106list $3.851
Discount
-40%
Unit
per 1M tokens
Cache read
from $0.165list $0.275
Context
1M
Max output
128K
Capability
152
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsText
Z.ai's flagship long-horizon reasoning and coding model with a 1M-token context window.
viaTencent Cloud TokenHub, Together AI, Alibaba Cloud (Model Studio Intl)
Doubao Seedance 2.0 Mini (260615)Video generationviaByteDance (Volcano Engine)
Video
$3.358per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
The lowest-cost Seedance 2.0 video model for 480p and 720p clips with native audio.
viaByteDance (Volcano Engine)
Claude Fable 5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $11.00
Output
from $55.00
Unit
per 1M tokens
Cache read
from $1.10
Context
1M
Max output
128K
Capability
163
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's most capable widely released Mythos-class model for demanding reasoning, long-horizon agentic work, software engineering, knowledge work, vision, and scientific research.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Gemini 3.5 Live TranslateviaGoogle (Gemini)
Input
$3.15list $3.50
Output
$18.90list $21.00
Discount
-10%
Unit
per 1M tokens
Cache read
$3.15list $3.50
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsAudioReturnsTextAudio
Google Gemini 3.5 low-latency speech-to-speech translation over the Live API, supporting 70+ languages. Outputs translated speech with a text transcript.
viaGoogle (Gemini)
MiniMax M3viaFireworks AI, MiniMax
Input
from $0.30
Output
from $1.20
Unit
per 1M tokens
Cache read
from $0.06
Context
1M
Max output
524K
Capability
147
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideo
MiniMax's multimodal reasoning model for long-context coding, perception, and agent planning.
viaFireworks AI, MiniMax
Grok Imagine Video 1.5Video generationviaxAI
Video
$0.088per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsVideo
xAI's flagship video model with native 1080p text-to-video and lip-synced audio.
viaxAI
Claude Opus 4.8viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $5.50
Output
from $27.50
Unit
per 1M tokens
Cache read
from $0.55
Context
1M
Max output
128K
Capability
160
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's latest Opus model with stronger agentic coding, long-context work, and advanced reasoning capabilities.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Opus 4.8 (Reseller)viaReseller (managed pool)
Input
$1.50
Output
$7.50
Unit
per 1M tokens
Cache read
$0.15
Context
200K
Max output
64K
Capability
160
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Opus 4.8 via third-party reseller channels with 200K context.
viaReseller (managed pool)
Gemini 3 Pro ImageviaGoogle (Gemini), Google Vertex AI
Input
$1.80list $2.00
Output
$10.80list $12.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.18list $0.20
Context
1M
Max output
64K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDFReturnsTextImage
Gemini 3 Pro with native image generation capabilities alongside text understanding.
viaGoogle (Gemini), Google Vertex AI
Gemini 3.1 Flash Image (Nano Banana 2)viaGoogle (Gemini), Google Vertex AI
Input
$0.45list $0.50
Output
$2.70list $3.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.045list $0.05
Context
128K
Max output
8K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDFReturnsTextImage
Google's latest image generation model combining Nano Banana Pro's advanced capabilities with Gemini Flash's speed. Supports text and image input, outputs text and images up to 4K resolution.
viaGoogle (Gemini), Google Vertex AI
Doubao Seed 2.0 Lite (260428)viaByteDance (Volcano Engine)
Input
$0.0876
Output
$0.5256
Unit
per 1M tokens
Cache read
$0.01752
Context
256K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudio
A lower-cost Doubao Seed 2.0 model for everyday multimodal workloads.
viaByteDance (Volcano Engine)
Gemini 3.5 FlashviaGoogle Vertex AI
Input
$1.35list $1.50
Output
$8.10list $9.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.135list $0.15
Context
1M
Max output
66K
Capability
155
First token
—
30-day uptime
—
AcceptsTextImageAudioVideoPDF
Gemini 3.5 Flash. Fast multimodal Gemini 3 model with reasoning, tool calling, structured output, and prompt caching.
viaGoogle Vertex AI
Gemini 3.1 Flash LiteviaGoogle (Gemini), Google Vertex AI
Input
$0.225list $0.25
Output
$1.35list $1.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0225list $0.025
Context
1M
Max output
66K
Capability
144
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Google's most cost-efficient Gemini model. Optimized for low latency, high-volume use cases at a fraction of the cost of larger models.
viaGoogle (Gemini), Google Vertex AI
Doubao Seed 2.0 Mini (260428)viaByteDance (Volcano Engine)
Input
$0.0292
Output
$0.292
Unit
per 1M tokens
Cache read
$0.00584
Context
262K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudio
The smallest Doubao Seed 2.0 variant for ultra-low-cost multimodal tasks, with audio input.
viaByteDance (Volcano Engine)
GPT Realtime 2viaOpenAI
Input
$4.40
Output
$26.40
Unit
per 1M tokens
Cache read
$0.44
Context
128K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
GPT Realtime 2 responds to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
Mistral MediumviaMistral AI
Input
$1.65
Output
$8.25
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsImageText
Mistral AI's mid-tier multimodal model (Medium 3.5) for agentic and coding workloads.
viaMistral AI
DeepSeek V4 Pro 0423viaAlibaba Cloud (Model Studio Intl)
Input
$0.99list $1.65
Output
$1.9806list $3.301
Discount
-40%
Unit
per 1M tokens
Cache read
$0.0828list $0.138
Context
1M
Max output
384K
Capability
149
First token
—
30-day uptime
—
AcceptsText
DeepSeek V4 Pro 0423 preview weights, a higher-capability hybrid-thinking model with 1M context and 384K max output.
viaAlibaba Cloud (Model Studio Intl)
GPT-5.5viaAzure AI Foundry, OpenAI
Input
from $4.50list $5.00
Output
from $27.00list $30.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.45list $0.50
Context
1.1M
Max output
128K
Capability
159
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5.5 is OpenAI's latest frontier model, designed for stronger agentic execution, coding, tool use, and long-context task completion.
viaAzure AI Foundry, OpenAI
GPT-5.5 (Reseller)viaReseller (managed pool)
Input
$2.50
Output
$15.00
Unit
per 1M tokens
Cache read
$0.25
Context
1.1M
Max output
128K
Capability
159
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.5 via third-party reseller channels (Responses API).
viaReseller (managed pool)
GPT-5.5 ProviaOpenAI
Input
from $27.00list $30.00
Output
from $162.00list $180.00
Discount
-10%
Unit
per 1M tokens
Cache read
—
Context
1.1M
Max output
128K
Capability
163
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.5 Pro is the higher-accuracy GPT-5.5 variant for harder questions, deeper research, and more demanding end-to-end tasks.
viaOpenAI
Gemini Embedding 2EmbeddingsviaGoogle (Gemini)
Embedding input
$0.22per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Google's multimodal embedding model with flexible 128–3072-dim vectors for semantic search, retrieval, and recommendation.
viaGoogle (Gemini)
GPT Image 2Image generationviaAzure AI Foundry, OpenAI
Image output
$27.00list $30.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageReturnsImage
OpenAI second-generation image model for high-quality image generation and editing with flexible sizes.
viaAzure AI Foundry, OpenAI
Doubao Seed 2.0 Code Preview (260215)viaByteDance (Volcano Engine)
Input
$0.4672
Output
$2.336
Unit
per 1M tokens
Cache read
$0.09344
Context
256K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
A preview Doubao Seed 2.0 model optimized for code generation and code understanding.
viaByteDance (Volcano Engine)
Doubao Seed 2.0 Pro (260215)viaByteDance (Volcano Engine)
Input
$0.4672
Output
$2.336
Unit
per 1M tokens
Cache read
$0.09344
Context
256K
Max output
32K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
ByteDance's flagship Doubao Seed 2.0 model for high-performance multimodal reasoning and generation.
viaByteDance (Volcano Engine)
Claude Opus 4.7viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $5.50
Output
from $27.50
Unit
per 1M tokens
Cache read
from $0.55
Context
1M
Max output
128K
Capability
157
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's latest Opus model with stronger advanced software engineering and higher-resolution vision.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Opus 4.7 (Reseller)viaReseller (managed pool)
Input
$1.50
Output
$7.50
Unit
per 1M tokens
Cache read
$0.15
Context
200K
Max output
64K
Capability
157
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Opus 4.7 via third-party reseller channels with 200K context.
viaReseller (managed pool)
GLM-5.1viaZhipu AI (ChatGLM), Alibaba Cloud (Model Studio Intl)
Input
from $0.66list $0.825
Output
from $2.6408list $3.301
Discount
-20%
Unit
per 1M tokens
Cache read
from $0.132list $0.165
Context
200K
Max output
128K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
Z.ai's flagship model for long-horizon agents and complex engineering tasks.
viaZhipu AI (ChatGLM), Alibaba Cloud (Model Studio Intl)
GPT-5.4 MiniviaAzure AI Foundry, OpenAI
Input
$0.675list $0.75
Output
$4.05list $4.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
400K
Max output
128K
Capability
149
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's most capable small model. Fast and efficient for coding, reasoning, and multimodal tasks. Approaches GPT-5.4 performance at lower cost and latency.
viaAzure AI Foundry, OpenAI
GPT-5.4 NanoviaAzure AI Foundry, OpenAI
Input
$0.18list $0.20
Output
$1.125list $1.25
Discount
-10%
Unit
per 1M tokens
Cache read
$0.018list $0.02
Context
400K
Max output
128K
Capability
146
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's smallest, cheapest GPT-5.4 variant. Optimized for classification, data extraction, ranking, and coding subagents where speed and cost matter most.
viaAzure AI Foundry, OpenAI
GLM-5V TurboviaZhipu AI (ChatGLM)
Input
$0.803
Output
$3.5332
Unit
per 1M tokens
Cache read
$0.19272
Context
200K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoPDF
GLM-5 multimodal model for agentic coding workflows over text, images, video, and documents.
viaZhipu AI (ChatGLM)
Mistral SmallviaMistral AI
Input
$0.165
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsImageText
Mistral AI's lightweight hybrid instruct/reasoning/coding model (Small 4, 119B/6.5B active).
viaMistral AI
Gemini 3.1 Flash LiveviaGoogle (Gemini)
Input
$0.675list $0.75
Output
$4.05list $4.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.675list $0.75
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudioVideoReturnsTextAudio
Google Gemini 3.1 Flash real-time bidirectional Live API model. Supports text, image, audio, and video input with text and audio output.
viaGoogle (Gemini)
Grok 4.20 (0309, Non-Reasoning)viaxAI
Input
$1.375
Output
$2.75
Unit
per 1M tokens
Cache read
$0.22
Context
2M
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
A non-reasoning Grok 4.20 snapshot for fast multimodal chat, tool use, and structured outputs.
viaxAI
Grok 4.20 (0309, Reasoning)viaxAI
Input
$1.375
Output
$2.75
Unit
per 1M tokens
Cache read
$0.22
Context
2M
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
A reasoning-enabled Grok 4.20 snapshot for long-context multimodal problem solving.
viaxAI
Grok 4.20 Multi-Agent (0309)viaxAI
Input
$1.375
Output
$2.75
Unit
per 1M tokens
Cache read
$0.22
Context
2M
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
A multi-agent Grok 4.20 snapshot designed for coordinated reasoning across multiple agents.
viaxAI
GPT-5.4viaAzure AI Foundry, OpenAI
Input
from $2.25list $2.50
Output
from $13.50list $15.00
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.225list $0.25
Context
1.1M
Max output
128K
Capability
157
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
OpenAI's latest frontier model, unifying the Codex and GPT lines. Features 1M+ token context window with strong coding, document understanding, and tool use.
viaAzure AI Foundry, OpenAI
GPT-5.4 Mini (Reseller)viaReseller (managed pool)
Input
$0.375
Output
$2.25
Unit
per 1M tokens
Cache read
$0.0375
Context
1.1M
Max output
128K
Capability
149
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.4 Mini via third-party reseller channels (Responses API).
viaReseller (managed pool)
Kling Video 3.0Video generationviaTencent Cloud TokenHub
Video
$1.46per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageReturnsVideo
Kuaishou's Kling 3.0 video model for text-to-video and first and last frame clips up to 4K.
viaTencent Cloud TokenHub
Kling Video 3.0 OmniVideo generationviaTencent Cloud TokenHub
Video
$1.46per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoReturnsVideo
Kuaishou's Kling 3.0 Omni video model for text, first and last frame, and image or video reference generation up to 4K.
viaTencent Cloud TokenHub
GPT Audio 1.5viaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioReturnsTextAudio
OpenAI's audio model for the Chat Completions API. It accepts audio inputs and produces audio outputs.
viaOpenAI
GPT Realtime 1.5viaOpenAI
Input
$4.40
Output
$17.60
Unit
per 1M tokens
Cache read
$0.44
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
GPT Realtime 1.5 responds to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
Claude Sonnet 4.6viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $3.30
Output
from $16.50
Unit
per 1M tokens
Cache read
from $0.33
Context
1M
Max output
128K
Capability
153
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's latest Sonnet model with improved coding, analysis, and complex reasoning capabilities.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Sonnet 4.6 (Reseller)viaReseller (managed pool)
Input
$0.90
Output
$4.50
Unit
per 1M tokens
Cache read
$0.09
Context
200K
Max output
64K
Capability
153
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Sonnet 4.6 via third-party reseller channels with 200K context.
viaReseller (managed pool)
Gemini 3.1 Pro PreviewviaGoogle (Gemini), Google Vertex AI
Input
$1.80list $2.00
Output
$10.80list $12.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.18list $0.20
Context
1M
Max output
64K
Capability
155
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioVideoPDF
Preview of Gemini 3.1 Pro. Latest evolution of Google's most capable model with improved reasoning.
viaGoogle (Gemini), Google Vertex AI
MiniMax M2viaAmazon Bedrock
Input
$0.33
Output
$1.32
Unit
per 1M tokens
Cache read
—
Context
205K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsText
MiniMax M2 model for long-context text generation and agent workloads.
viaAmazon Bedrock
MiniMax M2.1viaAmazon Bedrock
Input
$0.33
Output
$1.32
Unit
per 1M tokens
Cache read
—
Context
205K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsText
MiniMax M2.1 model for long-context text generation and agent workloads.
viaAmazon Bedrock
MiniMax M2.5viaAmazon Bedrock
Input
$0.33
Output
$1.32
Unit
per 1M tokens
Cache read
—
Context
205K
Max output
66K
Capability
147
First token
—
30-day uptime
—
AcceptsText
MiniMax's flagship M2.5 model (230B MoE, 10B active). Production-level agent model with function calling, structured output, and reasoning.
viaAmazon Bedrock
Claude Opus 4.6viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $5.50
Output
from $27.50
Unit
per 1M tokens
Cache read
from $0.55
Context
1M
Max output
128K
Capability
156
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Anthropic's most intelligent model for building agents and coding tasks.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Opus 4.6 (Reseller)viaReseller (managed pool)
Input
$1.50
Output
$7.50
Unit
per 1M tokens
Cache read
$0.15
Context
200K
Max output
64K
Capability
156
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Opus 4.6 via third-party reseller channels with 200K context.
viaReseller (managed pool)
GPT-5.3-CodexviaAzure AI Foundry, OpenAI
Input
$1.575list $1.75
Output
$12.60list $14.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1575list $0.175
Context
400K
Max output
128K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5.3-Codex is the latest version of the Codex series, optimized for long-horizon, agentic coding tasks. It's available in the Responses API only and supports low, medium, high, and xhigh reasoning effort settings.
viaAzure AI Foundry, OpenAI
Doubao Seedance 2.0 (260128)Video generationviaByteDance (Volcano Engine)
Video
$6.716per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
ByteDance's Seedance 2.0 video model with native audio, first and last frame control, and multimodal reference up to 4K.
viaByteDance (Volcano Engine)
Doubao Seedance 2.0 Fast (260128)Video generationviaByteDance (Volcano Engine)
Video
$5.402per 1M tokens
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
A faster, lower-cost Seedance 2.0 video model for 480p and 720p clips with native audio.
viaByteDance (Volcano Engine)
Grok Imagine VideoVideo generationviaxAI
Video
$0.055per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsVideo
xAI's first-generation video model for text-to-video clips up to 720p.
viaxAI
Kimi K2 ThinkingviaAmazon Bedrock
Input
$0.66
Output
$2.75
Unit
per 1M tokens
Cache read
—
Context
262K
Max output
262K
Capability
146
First token
—
30-day uptime
—
AcceptsTextImage
Moonshot AI's reasoning-enhanced Kimi K2 model with extended thinking capabilities for complex problem-solving.
viaAmazon Bedrock
Kimi K2.5viaAlibaba Cloud (Model Studio Intl), Amazon Bedrock
Input
from $0.4592list $0.574
Output
from $2.4088list $3.011
Discount
-20%
Unit
per 1M tokens
Cache read
$0.092list $0.115
Context
262K
Max output
262K
Capability
148
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
Moonshot AI's flagship Kimi K2.5 MoE model (1.04T params, 32B active) with native vision, advanced reasoning, and 256K context.
viaAlibaba Cloud (Model Studio Intl), Amazon Bedrock
GLM-4.7viaZhipu AI (ChatGLM), Amazon Bedrock
Input
from $0.3212
Output
from $1.2848
Unit
per 1M tokens
Cache read
$0.06424
Context
200K
Max output
128K
Capability
144
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
GLM-4.7 is Z.AI's flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.
viaZhipu AI (ChatGLM), Amazon Bedrock
Gemini 3 Flash PreviewviaGoogle (Gemini), Google Vertex AI
Input
$0.45list $0.50
Output
$2.70list $3.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.045list $0.05
Context
1M
Max output
64K
Capability
152
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageVideoPDF
Gemini 3 Flash Preview, optimized for speed with frontier intelligence combined with superior search and grounding capabilities.
viaGoogle (Gemini), Google Vertex AI
GPT Image 1.5Image generationviaAzure AI Foundry, OpenAI
Image output
$28.80list $32.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageReturnsImage
OpenAI improved image generation model with faster generation, better editing fidelity, and partial image streaming support.
viaAzure AI Foundry, OpenAI
GPT Realtime Mini (2025-12-15)viaOpenAI
Input
$0.66
Output
$2.64
Unit
per 1M tokens
Cache read
$0.066
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
A cost-efficient version of GPT Realtime - capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
GPT-5.2viaAzure AI Foundry, OpenAI
Input
$1.575list $1.75
Output
$12.60list $14.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1575list $0.175
Context
400K
Max output
128K
Capability
154
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5.2 is OpenAI's best model for coding and agentic tasks across industries.
viaAzure AI Foundry, OpenAI
GLM-5viaZhipu AI (ChatGLM), Amazon Bedrock
Input
from $0.6424
Output
from $2.8908
Unit
per 1M tokens
Cache read
$0.1606
Context
128K
Max output
16K
Capability
146
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
Z.ai's latest large language model with strong performance on reasoning, coding, and general knowledge tasks.
viaZhipu AI (ChatGLM), Amazon Bedrock
GPT-5.1viaAzure AI Foundry, OpenAI
Input
$1.125list $1.25
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1125list $0.125
Context
400K
Max output
128K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageAudioReturnsTextImageAudio
GPT-5.1 is the OpenAI's best model for coding and agentic tasks across industries.
viaAzure AI Foundry, OpenAI
GPT-5.1viaOpenAI
Input
$1.125list $1.25
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1125list $0.125
Context
400K
Max output
128K
Capability
150
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5.1 is the OpenAI's best model for coding and agentic tasks across industries.
viaOpenAI
Claude Opus 4.5viaAnthropic, Anthropic (AWS)
Input
$5.50
Output
$27.50
Unit
per 1M tokens
Cache read
$0.55
Context
200K
Max output
64K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDF
Anthropic's latest and most advanced Claude model, powering Claude Code.
viaAnthropic, Anthropic (AWS)
Claude Opus 4.5 (20251101)viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $5.50
Output
from $27.50
Unit
per 1M tokens
Cache read
from $0.55
Context
200K
Max output
64K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
November 2025 snapshot of Claude Opus 4.5, Anthropic's latest and most advanced model.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
GPT OSS Safeguard 120BviaAmazon Bedrock
Input
$0.165
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
OpenAI GPT OSS Safeguard 120B model for safety classification and guardrail workloads.
viaAmazon Bedrock
GPT OSS Safeguard 20BviaAmazon Bedrock
Input
$0.077
Output
$0.22
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
OpenAI GPT OSS Safeguard 20B model for lower-latency safety classification and guardrail workloads.
viaAmazon Bedrock
Claude Haiku 4.5viaAnthropic, Anthropic (AWS)
Input
$1.10
Output
$5.50
Unit
per 1M tokens
Cache read
$0.11
Context
200K
Max output
64K
Capability
142
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDF
The fastest model in the Claude 4.5 family. Offers quick responses with strong performance for everyday tasks.
viaAnthropic, Anthropic (AWS)
Claude Haiku 4.5viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Input
from $1.10
Output
from $5.50
Unit
per 1M tokens
Cache read
from $0.11
Context
200K
Max output
64K
Capability
142
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsTextImagePDF
Snapshot of Claude Haiku 4.5 from October 1, 2025. Fast model for everyday tasks.
viaAnthropic, Amazon Bedrock, Anthropic (AWS)
Claude Haiku 4.5 (Reseller)viaReseller (managed pool)
Input
$0.30
Output
$1.50
Unit
per 1M tokens
Cache read
$0.03
Context
200K
Max output
64K
Capability
142
First token
—
30-day uptime
—
AcceptsTextImagePDF
Claude Haiku 4.5 (October 1, 2025 snapshot) via third-party reseller channels with 200K context.
viaReseller (managed pool)
GLM-4.6viaZhipu AI (ChatGLM)
Input
$0.3212
Output
$1.2848
Unit
per 1M tokens
Cache read
$0.06424
Context
205K
Max output
205K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Latest GLM model from Zhipu AI with improved reasoning and generation capabilities.
viaZhipu AI (ChatGLM)
GPT AudioviaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.225list $0.25
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioReturnsTextAudio
The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
viaOpenAI
GPT Audio (2025-08-28)viaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.225list $0.25
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioReturnsTextAudio
The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
viaOpenAI
GPT Audio MiniviaOpenAI
Input
$0.54list $0.60
Output
$2.16list $2.40
Discount
-10%
Unit
per 1M tokens
Cache read
$0.054list $0.06
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioReturnsTextAudio
A cost-efficient version of GPT Audio. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.
viaOpenAI
GPT Image 1 MiniImage generationviaAzure AI Foundry, OpenAI
Image output
$7.20list $8.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImageReturnsImage
OpenAI low-cost image generation model for fast image generation and editing tasks.
viaAzure AI Foundry, OpenAI
GPT RealtimeviaOpenAI
Input
$4.40
Output
$17.60
Unit
per 1M tokens
Cache read
$0.44
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
GPT RealtimeviaOpenAI
Input
$4.40
Output
$17.60
Unit
per 1M tokens
Cache read
$0.44
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
GPT Realtime MiniviaOpenAI
Input
$0.66
Output
$2.64
Unit
per 1M tokens
Cache read
$0.066
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioImageReturnsTextAudio
A cost-efficient version of GPT Realtime - capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.
viaOpenAI
GPT-5 ProviaOpenAI
Input
$13.50list $15.00
Output
$108.00list $120.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.35list $1.50
Context
400K
Max output
272K
Capability
151
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5 pro uses more compute to think harder and provide consistently better answers.
viaOpenAI
GPT-5 ProviaOpenAI
Input
$13.50list $15.00
Output
$108.00list $120.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.35list $1.50
Context
400K
Max output
272K
Capability
151
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5 pro uses more compute to think harder and provide consistently better answers.
viaOpenAI
Qwen3 VL 235B A22B InstructviaAmazon Bedrock
Input
$0.583
Output
$2.926
Unit
per 1M tokens
Cache read
—
Context
262K
Max output
262K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Qwen3 VL 235B A22B vision-language model for text and image understanding.
viaAmazon Bedrock
Gemini 2.5 Flash ImageviaGoogle (Gemini), Google Vertex AI
Input
$0.27list $0.30
Output
$2.25list $2.50
Discount
-10%
Unit
per 1M tokens
Cache read
$0.27list $0.30
Context
128K
Max output
8K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImagePDFReturnsTextImage
Gemini 2.5 Flash with native image generation capabilities alongside text and image understanding.
viaGoogle (Gemini), Google Vertex AI
Qwen3 Coder 30B A3B InstructviaAmazon Bedrock
Input
$0.165
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
262K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Qwen3 Coder 30B A3B model for coding and agentic software engineering tasks.
viaAmazon Bedrock
Qwen3 Coder 480B A35B InstructviaAmazon Bedrock
Input
$0.495
Output
$1.98
Unit
per 1M tokens
Cache read
—
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Qwen3 Coder 480B A35B model for large-scale coding and agentic software engineering tasks.
viaAmazon Bedrock
Qwen3 Coder NextviaAmazon Bedrock
Input
$0.55
Output
$1.32
Unit
per 1M tokens
Cache read
—
Context
131K
Max output
66K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Qwen3 Coder Next model for coding and agentic software engineering tasks.
viaAmazon Bedrock
Qwen3 Next 80B A3B InstructviaAmazon Bedrock
Input
$0.154
Output
$1.32
Unit
per 1M tokens
Cache read
—
Context
262K
Max output
262K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Qwen3 Next 80B A3B model for long-context instruction following.
viaAmazon Bedrock
o3-proviaOpenAI
Input
$18.00list $20.00
Output
$72.00list $80.00
Discount
-10%
Unit
per 1M tokens
Cache read
$4.50list $5.00
Context
200K
Max output
100K
Capability
147
First token
—
30-day uptime
—
AcceptsTextImage
Our most capable reasoning model, using more compute for the best possible answers on the hardest problems.
viaOpenAI
o3-pro (2025-06-10)viaOpenAI
Input
$18.00list $20.00
Output
$72.00list $80.00
Discount
-10%
Unit
per 1M tokens
Cache read
$4.50list $5.00
Context
200K
Max output
100K
Capability
147
First token
—
30-day uptime
—
AcceptsTextImage
Snapshot of o3-pro from June 10, 2025. Our most capable reasoning model for the hardest problems.
viaOpenAI
Gemini 2.5 Flash Native Audio (Live)viaGoogle (Gemini)
Input
$0.45list $0.50
Output
$1.80list $2.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
1M
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudioReturnsTextAudio
Google Gemini 2.5 Flash real-time bidirectional voice model. Supports text and audio input/output. Provides low-latency voice conversations via Live API (WebSocket).
viaGoogle (Gemini)
Magistral Small 1.2viaAmazon Bedrock
Input
$0.55
Output
$1.65
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
40K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Mistral Magistral Small 1.2 reasoning model with structured output support.
viaAmazon Bedrock
GPT OSS 20BviaGroq, Amazon Bedrock
Input
from $0.077
Output
$0.33
Unit
per 1M tokens
Cache read
$0.041252
Context
128K
Max output
16K
Capability
138
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
OpenAI's open-weight 20B model for lower latency and local use cases.
viaGroq, Amazon Bedrock
DeepSeek V3.1viaAmazon Bedrock
Input
$0.638
Output
$1.848
Unit
per 1M tokens
Cache read
$0.0638
Context
128K
Max output
16K
Capability
140
First token
—
30-day uptime
—
AcceptsText
DeepSeek V3.1 hybrid model combining V3 and R1 capabilities with 128K context.
viaAmazon Bedrock
GPT OSS 120BviaCerebras, Groq, Together AI, Amazon Bedrock
Input
from $0.165
Output
from $0.66
Unit
per 1M tokens
Cache read
from $0.0825
Context
128K
Max output
16K
Capability
140
First token
—
30-day uptime
—
Providers
lowest of 4 providers
AcceptsText
OpenAI's open-weight 120B model for production and high reasoning use cases.
viaCerebras, Groq, Together AI, Amazon Bedrock
GLM-4.5 AirviaZhipu AI (ChatGLM)
Input
$0.12848
Output
$0.3212
Unit
per 1M tokens
Cache read
$0.025696
Context
131K
Max output
98K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Zhipu AI's lightweight GLM-4.5 variant for cost-effective tasks.
viaZhipu AI (ChatGLM)
GLM-4.5 AirXviaZhipu AI (ChatGLM)
Input
$0.6424
Output
$1.9272
Unit
per 1M tokens
Cache read
$0.12848
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Zhipu AI's GLM-4.5 AirX variant optimized for high-speed inference.
viaZhipu AI (ChatGLM)
GLM-4.5VviaZhipu AI (ChatGLM)
Input
$0.3212
Output
$0.9636
Unit
per 1M tokens
Cache read
$0.06424
Context
64K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideo
Zhipu AI's multimodal model with vision capabilities. Processes text and images for analysis tasks.
viaZhipu AI (ChatGLM)
GPT-5viaAzure AI Foundry, OpenAI
Input
$1.125list $1.25
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1125list $0.125
Context
400K
Max output
128K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5 is OpenAI's flagship model for coding, reasoning, and agentic tasks across domains.
viaAzure AI Foundry, OpenAI
GPT-5 (2025-08-07)viaOpenAI
Input
$1.125list $1.25
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.1125list $0.125
Context
400K
Max output
128K
Capability
150
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5 is our flagship model for coding, reasoning, and agentic tasks across domains.
viaOpenAI
GPT-5 MiniviaAzure AI Foundry, OpenAI
Input
$0.225list $0.25
Output
$1.80list $2.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0225list $0.025
Context
400K
Max output
128K
Capability
145
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.
viaAzure AI Foundry, OpenAI
GPT-5 Mini (2025-08-07)viaOpenAI
Input
$0.225list $0.25
Output
$1.80list $2.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0225list $0.025
Context
400K
Max output
128K
Capability
145
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5 mini is a faster, more cost-efficient version of GPT-5. It's great for well-defined tasks and precise prompts.
viaOpenAI
GPT-5 NanoviaAzure AI Foundry, OpenAI
Input
$0.045list $0.05
Output
$0.36list $0.40
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0045list $0.005
Context
400K
Max output
128K
Capability
139
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.
viaAzure AI Foundry, OpenAI
GPT-5 Nano (2025-08-07)viaOpenAI
Input
$0.045list $0.05
Output
$0.36list $0.40
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0045list $0.005
Context
400K
Max output
128K
Capability
139
First token
—
30-day uptime
—
AcceptsTextImage
GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.
viaOpenAI
Claude Opus 4.1 (20250805)viaAmazon Bedrock
Input
$16.50
Output
$82.50
Unit
per 1M tokens
Cache read
$1.65
Context
200K
Max output
32K
Capability
144
First token
—
30-day uptime
—
AcceptsTextImagePDF
August 2025 snapshot of Claude Opus 4.1, Anthropic's most capable model for complex tasks.
viaAmazon Bedrock
Voxtral Mini 3B 2507viaAmazon Bedrock
Input
$0.044
Output
$0.044
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudio
Mistral Voxtral Mini 3B model with text and audio input support.
viaAmazon Bedrock
Voxtral Small 24B 2507viaAmazon Bedrock
Input
$0.11
Output
$0.33
Unit
per 1M tokens
Cache read
—
Context
32K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsTextAudio
Mistral Voxtral Small 24B model with text and audio input support.
viaAmazon Bedrock
Rerank v4.0 FastRerankviaCohere
Rerank
$0.0022per query
Context
33K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere's Rerank v4.0 Fast model with 32K context for high-throughput document reranking.
viaCohere
Rerank v4.0 ProRerankviaCohere
Rerank
$0.002752per query
Context
33K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere's Rerank v4.0 Pro model with 32K context for high-precision document reranking.
viaCohere
Qwen3 235B A22BviaAmazon Bedrock
Input
$0.242
Output
$0.968
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
33K
Capability
139
First token
—
30-day uptime
—
AcceptsText
Qwen3 235B model with 22B active parameters optimized for throughput.
viaAmazon Bedrock
Qwen3 32BviaAmazon Bedrock
Input
$0.165
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
131K
Max output
16K
Capability
138
First token
—
30-day uptime
—
AcceptsText
Alibaba's Qwen3 32B model with strong reasoning and tool calling capabilities.
viaAmazon Bedrock
o3viaOpenAI
Input
$1.80list $2.00
Output
$7.20list $8.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
200K
Max output
100K
Capability
147
First token
—
30-day uptime
—
AcceptsTextImage
Our smartest reasoning model, trained to think for longer before responding. Excels at programming, business/consulting, and creative ideation with breakthrough performance on complex tasks.
viaOpenAI
o3 (2025-04-16)viaOpenAI
Input
$1.80list $2.00
Output
$7.20list $8.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
200K
Max output
100K
Capability
147
First token
—
30-day uptime
—
AcceptsTextImage
Snapshot of o3 from April 16, 2025. Our smartest reasoning model with breakthrough performance on complex tasks.
viaOpenAI
GPT-4.1 (2025-04-14)viaOpenAI
Input
$1.80list $2.00
Output
$7.20list $8.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
1M
Max output
33K
Capability
137
First token
—
30-day uptime
—
AcceptsTextImage
Snapshot of GPT-4.1 from April 14, 2025, providing enhanced instruction following and multimodal capabilities.
viaOpenAI
GPT-4.1 MiniviaOpenAI
Input
$0.36list $0.40
Output
$1.44list $1.60
Discount
-10%
Unit
per 1M tokens
Cache read
$0.09list $0.10
Context
1M
Max output
33K
Capability
135
First token
—
30-day uptime
—
AcceptsTextImage
GPT-4.1 Mini is a cost-efficient, faster version of GPT-4.1 optimized for everyday tasks and quick responses.
viaOpenAI
GPT-4.1 Mini (2025-04-14)viaOpenAI
Input
$0.36list $0.40
Output
$1.44list $1.60
Discount
-10%
Unit
per 1M tokens
Cache read
$0.09list $0.10
Context
1M
Max output
33K
Capability
135
First token
—
30-day uptime
—
AcceptsTextImage
Snapshot of GPT-4.1 Mini from April 14, 2025, optimized for cost-efficient everyday tasks.
viaOpenAI
Embed v4.0EmbeddingsviaCohere
Embedding input
$0.132per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Cohere's latest multimodal embedding model with 128K context, 1536-dim vectors, and image input support.
viaCohere
GPT-4o Mini TTSText to speechviaOpenAI
Speech
$10.80list $12.00-10%per 1M characters
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
OpenAI low-cost text-to-speech model based on GPT-4o Mini architecture.
viaOpenAI
GPT-4o Mini TranscribeSpeech to textviaOpenAI
Audio input
$2.70list $3.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsAudio
Lightweight speech recognition model based on GPT-4o Mini, lower cost audio token pricing.
viaOpenAI
GPT-4o TranscribeSpeech to textviaOpenAI
Audio input
$5.40list $6.00per 1M tokens
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsAudio
Advanced speech recognition model based on GPT-4o, supporting audio token pricing.
viaOpenAI
Aya Vision 32BviaCohere
Input
$0.55
Output
$1.65
Unit
per 1M tokens
Cache read
—
Context
16K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsImageText
Cohere Labs' flagship multilingual vision-language model with 32B parameters. Supports 23 languages for advanced vision-language tasks including OCR, captioning, visual reasoning, and image understanding.
viaCohere
Mistral OCROCRviaMistral AI
OCR
$0.0044per page
Context
1K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsImagePDF
Mistral document OCR model (Pixtral OCR) for PDF and image text recognition.
viaMistral AI
Azure TTS-1Text to speechviaAzure AI Foundry
Speech
$16.50per 1M characters
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
Microsoft Azure's text-to-speech service for natural voice synthesis.
viaAzure AI Foundry
Command A (03-2025)viaCohere
Input
$2.75
Output
$11.00
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere's flagship Command A model featuring advanced reasoning capabilities and 256K context. Optimized for enterprise use cases requiring sophisticated analysis and instruction following.
viaCohere
Command R (08-2024)viaCohere
Input
$0.165
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
August 2024 update of Command R with enhanced reasoning abilities and improved instruction following. Features better multilingual support and tool calling capabilities.
viaCohere
Command R+ (08-2024)viaCohere
Input
$2.75
Output
$11.00
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
August 2024 update of Command R+ with advanced reasoning and improved capabilities. Features enhanced tool use and better performance on complex analytical tasks.
viaCohere
Command R7B (12-2024)viaCohere
Input
$0.041252
Output
$0.165
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Compact 7B parameter Command R model from December 2024, balancing efficiency with capability. Ideal for cost-effective deployment while maintaining strong performance on core tasks.
viaCohere
GLM-4 LongviaZhipu AI (ChatGLM)
Input
$0.1606
Output
$0.1606
Unit
per 1M tokens
Cache read
$0.0803
Context
1M
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
GLM-4 variant with extended 1M token context window for processing very long documents.
viaZhipu AI (ChatGLM)
Mistral LargeviaMistral AI
Input
$0.55
Output
$1.65
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsImageText
Mistral AI's flagship model for complex reasoning, coding, and multilingual tasks.
viaMistral AI
WhisperSpeech to textviaOpenAI
Transcription
$0.000092list $0.0001-8%per second
Context
128K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsAudio
General-purpose speech recognition model. Transcribes and translates audio to text in multiple languages.
viaOpenAI
CodestralviaMistral AI
Input
$0.33
Output
$0.99
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Mistral AI's code-specialized model with 256K context for code generation, review, and completion.
viaMistral AI
Devstral 2 123BviaAmazon Bedrock
Input
$0.44
Output
$2.20
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Mistral Devstral 2 123B model for coding and software engineering agent tasks.
viaAmazon Bedrock
Gemma 3 12B ITviaAmazon Bedrock
Input
$0.099
Output
$0.319
Unit
per 1M tokens
Cache read
—
Context
131K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Google Gemma 3 12B instruction-tuned model with structured output support.
viaAmazon Bedrock
Gemma 3 27B InstructviaAmazon Bedrock
Input
$0.253
Output
$0.418
Unit
per 1M tokens
Cache read
—
Context
203K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Google Gemma 3 27B instruction-tuned model with vision input and structured output support.
viaAmazon Bedrock
Gemma 3 4B ITviaAmazon Bedrock
Input
$0.044
Output
$0.088
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Google Gemma 3 4B instruction-tuned model for efficient text and lightweight multimodal tasks.
viaAmazon Bedrock
Ministral 14B 3.0viaMistral AI, Amazon Bedrock
Input
$0.22
Output
$0.22
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
Mistral Ministral 14B 3.0 compact text model with structured output support.
viaMistral AI, Amazon Bedrock
Ministral 3 3BviaMistral AI, Amazon Bedrock
Input
$0.11
Output
$0.11
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
8K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
Mistral Ministral 3 3B compact multimodal model with structured output support.
viaMistral AI, Amazon Bedrock
Ministral 3 8BviaMistral AI, Amazon Bedrock
Input
$0.165
Output
$0.165
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
Mistral Ministral 3 8B compact text model with structured output support.
viaMistral AI, Amazon Bedrock
Mistral Large 3viaAmazon Bedrock
Input
$0.55
Output
$1.65
Unit
per 1M tokens
Cache read
—
Context
256K
Max output
8K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Mistral Large 3 675B Instruct model for multilingual reasoning, coding, and long-context generation.
viaAmazon Bedrock
NVIDIA Nemotron 3 Super 120BviaAmazon Bedrock
Input
$0.165
Output
$0.715
Unit
per 1M tokens
Cache read
—
Context
262K
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsText
NVIDIA Nemotron 3 Super 120B A12B model for long-context language and agent workloads.
viaAmazon Bedrock
NVIDIA Nemotron Nano 12B v2viaAmazon Bedrock
Input
$0.22
Output
$0.66
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
NVIDIA Nemotron Nano 12B v2 vision-language model for efficient multimodal tasks.
viaAmazon Bedrock
NVIDIA Nemotron Nano 3 30BviaAmazon Bedrock
Input
$0.066
Output
$0.264
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
NVIDIA Nemotron Nano 3 30B model for efficient text generation and agent tasks.
viaAmazon Bedrock
NVIDIA Nemotron Nano 9B v2viaAmazon Bedrock
Input
$0.066
Output
$0.253
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
NVIDIA Nemotron Nano 9B v2 model for efficient language tasks with tool calling and structured output.
viaAmazon Bedrock
GPT-4o (2024-11-20)viaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.125list $1.25
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
November 2024 snapshot of GPT-4 Omni with enhanced creative writing and coding capabilities.
viaOpenAI
Aya Expanse 32BviaCohere
Input
$0.55
Output
$1.65
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere Labs' flagship multilingual 32B model supporting 23 languages with 128K context. State-of-the-art performance rivaling larger models like Llama 3.1 70B for multilingual tasks.
viaCohere
GPT-4o (2024-08-06)viaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.125list $1.25
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
August 2024 snapshot of GPT-4 Omni with improved structured outputs and function calling.
viaOpenAI
GPT-4o-miniviaOpenAI
Input
$0.135list $0.15
Output
$0.54list $0.60
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
128K
Max output
16K
Capability
126
First token
—
30-day uptime
—
AcceptsTextImage
A fast, affordable small model for lightweight tasks with vision and text capabilities.
viaOpenAI
GPT-4o-mini (2024-07-18)viaOpenAI
Input
$0.135list $0.15
Output
$0.54list $0.60
Discount
-10%
Unit
per 1M tokens
Cache read
$0.0675list $0.075
Context
128K
Max output
16K
Capability
126
First token
—
30-day uptime
—
AcceptsTextImage
July 2024 snapshot of GPT-4o-mini, the initial release of OpenAI's affordable small model.
viaOpenAI
GPT-4 OmniviaOpenAI
Input
$2.25list $2.50
Output
$9.00list $10.00
Discount
-10%
Unit
per 1M tokens
Cache read
$1.125list $1.25
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
OpenAI's flagship multimodal model combining text and vision capabilities with GPT-4 level intelligence.
viaOpenAI
Rerank English v3.0RerankviaCohere
Rerank
$0.0022per query
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere Rerank English v3.0, high-precision English reranking model.
viaCohere
Rerank Multilingual v3.0RerankviaCohere
Rerank
$0.0022per query
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Cohere Rerank Multilingual v3.0, reranking model supporting 100+ languages.
viaCohere
TTS-1Text to speechviaOpenAI
Speech
$13.50list $15.00-10%per 1M characters
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
OpenAI standard text-to-speech model supporting multiple voices and formats.
viaOpenAI
TTS-1 (1106)Text to speechviaOpenAI
Speech
$13.50list $15.00-10%per 1M characters
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
TTS-1 November 2023 snapshot.
viaOpenAI
TTS-1 HDText to speechviaOpenAI
Speech
$27.00list $30.00-10%per 1M characters
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
OpenAI high-quality text-to-speech model with more natural audio.
viaOpenAI
TTS-1 HD (1106)Text to speechviaOpenAI
Speech
$27.00list $30.00-10%per 1M characters
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextReturnsAudio
TTS-1 HD November 2023 snapshot.
viaOpenAI
Text Embedding Ada 002EmbeddingsviaOpenAI
Embedding input
$0.09list $0.10-10%per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
OpenAI previous-generation embedding model, widely adopted.
viaOpenAI
Codestral Embed (2505)EmbeddingsviaMistral AI
Embedding input
$0.165per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Mistral AI code-specialized embedding model optimized for code search and retrieval.
viaMistral AI
DeepSeek ChatviaAmazon Bedrock
Input
$0.682
Output
$2.035
Unit
per 1M tokens
Cache read
$0.0682
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
DeepSeek V3-generation non-thinking chat model, served by third-party hosts.
viaAmazon Bedrock
DeepSeek V4 Pro 0813viaTogether AI, DeepSeek, Alibaba Cloud (Model Studio Intl)
Input
from $0.636
Output
from $1.908
Unit
per 1M tokens
Cache read
from $0.0219
Context
1M
Max output
384K
Capability
156
First token
—
30-day uptime
—
Providers
lowest of 3 providers
AcceptsText
DeepSeek V4 Pro 0813 production weights with 1M context and 384K max output, MIT open-sourced.
viaTogether AI, DeepSeek, Alibaba Cloud (Model Studio Intl)
Gemini Embedding 001EmbeddingsviaGoogle (Gemini)
Embedding input
$0.165per 1M tokens
Context
2K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Google Gemini embedding model with 3072-dim vectors for high-precision semantic search.
viaGoogle (Gemini)
GLM-4.6VviaZhipu AI (ChatGLM)
Input
$0.1606
Output
$0.4818
Unit
per 1M tokens
Cache read
$0.03212
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Vision-language model from Z.ai for image understanding, analysis, and visual Q&A.
viaZhipu AI (ChatGLM)
GLM-4.6V-FlashviaZhipu AI (ChatGLM)
Input
Free
Output
Free
Unit
per 1M tokens
Cache read
Free
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Free vision model from Z.ai for basic image understanding tasks.
viaZhipu AI (ChatGLM)
GLM-4.6V-FlashXviaZhipu AI (ChatGLM)
Input
$0.024092
Output
$0.2409
Unit
per 1M tokens
Cache read
$0.00482
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Fast vision model from Z.ai for high-volume image understanding at low cost.
viaZhipu AI (ChatGLM)
GLM-4.7-FlashviaZhipu AI (ChatGLM), Amazon Bedrock
Input
from Free
Output
from Free
Unit
per 1M tokens
Cache read
Free
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsText
Free-tier flash model from Z.ai for basic tasks and experimentation.
viaZhipu AI (ChatGLM), Amazon Bedrock
GLM-4.7-FlashXviaZhipu AI (ChatGLM)
Input
$0.0803
Output
$0.4818
Unit
per 1M tokens
Cache read
$0.01606
Context
128K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Ultra-fast, cost-efficient model from Z.ai for high-volume, latency-sensitive workloads.
viaZhipu AI (ChatGLM)
GLM-5-CodeviaZhipu AI (ChatGLM)
Input
$1.32
Output
$5.50
Unit
per 1M tokens
Cache read
—
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Code-specialized variant of GLM-5 from Z.ai, optimized for software engineering tasks.
viaZhipu AI (ChatGLM)
GLM-5-TurboviaZhipu AI (ChatGLM)
Input
$0.803
Output
$3.5332
Unit
per 1M tokens
Cache read
$0.19272
Context
128K
Max output
16K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Fast variant of GLM-5 from Z.ai, optimized for speed while retaining strong reasoning capabilities.
viaZhipu AI (ChatGLM)
GLM-5.3-FlashX-LegalviaZhipu AI (ChatGLM)
Input
$0.3212
Output
$1.1242
Unit
per 1M tokens
Cache read
$0.091544
Context
1M
Max output
131K
Capability
—
First token
—
30-day uptime
—
AcceptsText
GLM-5.3-FlashX further trained for legal research, contract review, and legal drafting.
viaZhipu AI (ChatGLM)
GLM-OCROCRviaZhipu AI (ChatGLM)
Input
$0.03212per 1M tokens
Context
100
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsImagePDF
OCR-specialized model from Z.ai for text extraction from images and documents.
viaZhipu AI (ChatGLM)
GPT-4.1viaOpenAI
Input
$1.80list $2.00
Output
$7.20list $8.00
Discount
-10%
Unit
per 1M tokens
Cache read
$0.45list $0.50
Context
1M
Max output
33K
Capability
137
First token
—
30-day uptime
—
AcceptsTextImage
GPT-4.1 is an enhanced version of GPT-4 with improved instruction following and multimodal capabilities for text and image understanding.
viaOpenAI
Grok 4.3viaxAI
Input
$1.375
Output
$2.75
Unit
per 1M tokens
Cache read
$0.22
Context
1M
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
xAI's reasoning model for agentic tool calling, instruction following, and multimodal text generation.
viaxAI
Grok 4.5viaxAI
Input
$2.20
Output
$6.60
Unit
per 1M tokens
Cache read
$0.33
Context
500K
Max output
128K
Capability
154
First token
—
30-day uptime
—
AcceptsTextImage
xAI's flagship reasoning model for multimodal chat, tool use, and structured outputs.
viaxAI
Grok 4.6viaxAI
Input
$2.20
Output
$6.60
Unit
per 1M tokens
Cache read
$0.55
Context
500K
Max output
128K
Capability
157
First token
—
30-day uptime
—
AcceptsTextImage
xAI's flagship reasoning model for long-running agents and interactive visual work.
viaxAI
Grok 4.7viaxAI
Input
$2.20
Output
$6.60
Unit
per 1M tokens
Cache read
$0.55
Context
500K
Max output
128K
Capability
155
First token
—
30-day uptime
—
AcceptsTextImage
xAI's frontier reasoning model for long-running coding and knowledge work, with stronger self-verification and long-context management.
viaxAI
Grok Build 0.1viaxAI
Input
$1.10
Output
$2.20
Unit
per 1M tokens
Cache read
$0.22
Context
256K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
xAI's coding model for agentic software engineering and workflow tasks.
viaxAI
Kimi K2.6viaMoonshot AI (Kimi)
Input
$1.0439
Output
$4.3362
Unit
per 1M tokens
Cache read
$0.17666
Context
262K
Max output
262K
Capability
151
First token
—
30-day uptime
—
AcceptsTextImage
Moonshot AI's multimodal Kimi K2.6 model for long-horizon coding and agentic work.
viaMoonshot AI (Kimi)
Kimi K2.7 CodeviaMoonshot AI (Kimi), Alibaba Cloud (Model Studio Intl)
Input
from $0.71512list $0.8939
Output
from $2.97048list $3.7131
Discount
-20%
Unit
per 1M tokens
Cache read
from $0.14304list $0.1788
Context
262K
Max output
262K
Capability
150
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
Moonshot AI's multimodal reasoning model optimized for coding and agentic software engineering.
viaMoonshot AI (Kimi), Alibaba Cloud (Model Studio Intl)
Kimi K2.7 Code HighSpeedviaMoonshot AI (Kimi)
Input
$2.0878
Output
$8.6724
Unit
per 1M tokens
Cache read
$0.41756
Context
262K
Max output
262K
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
Kimi K2.7 Code served at ~180 tokens/s for latency-sensitive coding agents.
viaMoonshot AI (Kimi)
MiniMax H3 HighspeedVideo generationviaMiniMax
Video
$0.03796per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
A faster MiniMax H3 video model for 480P and 768P clips with native audio.
viaMiniMax
MiniMax H3 LiteVideo generationviaMiniMax
Video
$0.02336per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageVideoAudioReturnsVideo
The lowest-cost MiniMax H3 video model for 480P and 768P clips with native audio.
viaMiniMax
MiniMax H3 MaxVideo generationviaMiniMax
Video
$0.04818per second
Context
4K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImageAudioReturnsVideo
A fast MiniMax H3 video model post-trained by fal for 480P and 768P clips with native audio.
viaMiniMax
Mistral EmbedEmbeddingsviaMistral AI
Embedding input
$0.11per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
Mistral AI general-purpose text embedding model with 8K context for semantic search and retrieval.
viaMistral AI
Omni Moderation (2024-09-26)ModerationviaOpenAI
Moderation
Freeper request
Context
33K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
OpenAI multimodal content moderation model, 2024-09-26 snapshot.
viaOpenAI
Omni Moderation LatestModerationviaOpenAI
Moderation
Freeper request
Context
33K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsTextImage
OpenAI latest multimodal content moderation model supporting text and image input.
viaOpenAI
Qwen3.8 MaxviaFireworks AI, Alibaba Cloud (Model Studio Intl)
Input
from $1.485list $1.65
Output
from $4.4559list $4.951
Discount
-10%
Unit
per 1M tokens
Cache read
from $0.1854list $0.206
Context
1M
Max output
131K
Capability
158
First token
—
30-day uptime
—
Providers
lowest of 2 providers
AcceptsTextImage
Alibaba's Qwen3.8 flagship with hybrid thinking (default on) and vision support.
viaFireworks AI, Alibaba Cloud (Model Studio Intl)
Tencent Hunyuan Role LatestviaTencent Cloud TokenHub
Input
$0.3504
Output
$1.4016
Unit
per 1M tokens
Cache read
—
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hunyuan roleplay model served by TokenHub for character dialogue and digital personas.
viaTencent Cloud TokenHub
Tencent Hy-MT2-LiteviaTencent Cloud TokenHub
Input
$0.0438
Output
$0.1752
Unit
per 1M tokens
Cache read
—
Context
8K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy-MT2-Lite translation model served by TokenHub.
viaTencent Cloud TokenHub
Tencent Hy-MT2-PlusviaTencent Cloud TokenHub
Input
$0.073
Output
$0.292
Unit
per 1M tokens
Cache read
—
Context
8K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy-MT2-Plus translation model served by TokenHub.
viaTencent Cloud TokenHub
Tencent Hy-MT2-ProviaTencent Cloud TokenHub
Input
$0.073
Output
$0.292
Unit
per 1M tokens
Cache read
—
Context
8K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy-MT2-Pro translation model served by TokenHub.
viaTencent Cloud TokenHub
Tencent Hy-RoleviaTencent Cloud TokenHub
Input
$0.3504
Output
$1.4016
Unit
per 1M tokens
Cache read
—
Context
32K
Max output
4K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy-Role roleplay model served by TokenHub for character dialogue and digital personas.
viaTencent Cloud TokenHub
Tencent Hy3viaTencent Cloud TokenHub
Input
$0.146
Output
$0.584
Unit
per 1M tokens
Cache read
$0.0365
Context
256K
Max output
128K
Capability
—
First token
—
30-day uptime
—
AcceptsText
Tencent Hy3 reasoning model served by TokenHub for long-context chat, agent, and code workloads.
viaTencent Cloud TokenHub
Text Embedding 3 LargeEmbeddingsviaOpenAI
Embedding input
$0.117list $0.13-10%per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
OpenAI latest large embedding model with highest precision.
viaOpenAI
Text Embedding 3 SmallEmbeddingsviaOpenAI
Embedding input
$0.018list $0.02-10%per 1M tokens
Context
8K
Max output
—
Capability
—
First token
—
30-day uptime
—
AcceptsText
OpenAI latest high-performance small embedding model with best cost efficiency.
viaOpenAI