Models & Pricing

Prices are configured in src/config/site.ts and are shown in USD per million tokens.

Zhipu

Long-context coding

GLM-5.2

glm-5.2

A long-context reasoning model for coding agents, tool use, and large document workflows that need stronger state retention.

1M contextCodingTool use

Input: $0.90
Output: $3.10

Moonshot

Agentic coding & reasoning

Kimi K3

kimi-k3

Moonshot's newest-generation Kimi model with an internal reasoning budget for agentic coding, tool use, and long-context problem solving.

Reasoning1M contextAgents

Input: $2.30
Output: $12.3

Moonshot

Agentic coding

Kimi K2.7 Code

kimi-k2.7-code

A coding-focused model for agentic programming, repository-level edits, and multi-step developer workflows.

CodeAgentsRepositories

Input: $0.72
Output: $3

Alibaba

Complex automation

Qwen3.7-Max

qwen3.7-max

The premium Qwen route for complex planning, multimodal automation, and higher-stakes product workflows.

FlagshipVisionPlanning

Input: $1.24
Output: $3.72

DeepSeek

Reasoning and debugging

DeepSeek V4 Pro

deepseek-v4-pro

A stronger DeepSeek tier for heavier reasoning, debugging, and multi-step product work with 1M context.

Reasoning1M contextDebugging

Input: $0.31
Output: $0.62

Alibaba

Multimodal agents

Qwen3.7-Plus

qwen3.7-plus-2026-05-26

A balanced multimodal model for agents that read screens, reason through product tasks, and write code without premium frontier pricing.

VisionCodingAgents

Input: $0.25
Output: $1.20

xAI

Reasoning & coding

Grok 4.5

grok-4.5

xAI's advanced reasoning and coding model for agents, analysis, and tool-assisted developer workflows.

ReasoningCodingAgents

Input: $1.40
Output: $4.20

Anthropic

Frontier coding & agents

Claude Opus 5

claude-opus-5

Anthropic's newest frontier flagship for the hardest coding, long-horizon agent runs, and deep reasoning, with up to 1M tokens of context.

FlagshipReasoningAgents

Input: $0.85
Output: $4.25

Anthropic

Hard coding & long-horizon agents

Claude Opus 4.8

claude-opus-4-8

Anthropic's frontier flagship for the hardest coding, agents, and long-horizon work through one OpenAI-compatible gateway.

FlagshipCodingAgents

Input: $3
Output: $15

Anthropic

Real-time agents & tool use

Claude Sonnet 5

claude-sonnet-5

Fast frontier intelligence for real-time agents, tool use, and computer use — the everyday Claude workhorse for low-latency workflows.

AgentsTool use1M context

Input: $1.20
Output: $6

Anthropic

Frontier reasoning

Claude Fable 5

claude-fable-5

Anthropic's most capable flagship for frontier reasoning, complex tool use, and long-horizon agents.

FlagshipFrontierAgents

Input: $7
Output: $35

Google

Multimodal reasoning & coding

Gemini 3.1 Pro

gemini-3.1-pro-preview

Google's high-capability multimodal model for complex reasoning, coding, and long-context work.

MultimodalReasoningLong context

Input: $1.20
Output: $7.20

OpenAI

Frontier agentic coding

GPT-5.5

gpt-5.5

OpenAI's frontier model for agentic coding, computer use, and knowledge work through one OpenAI-compatible gateway.

FlagshipCodingAgents

Input: $3
Output: $18

OpenAI

Balanced frontier + long context

GPT-5.6 Terra

gpt-5.6-terra

A balanced GPT-5.6 tier for frontier agents, tool use, and long-context coding.

FrontierAgentsLong context

Input: $1.75
Output: $10.5

Pricing table

Model	Provider	Use case	Input	Output
GLM-5.2`glm-5.2`	Zhipu	Long-context coding	$0.90/ 1MPublic ref.~~$1.40~~	$3.10/ 1MPublic ref.~~$4.40~~
Kimi K3`kimi-k3`	Moonshot	Agentic coding & reasoning	$2.30/ 1MPublic ref.$3	$12.3/ 1MPublic ref.~~$15~~
Kimi K2.7 Code`kimi-k2.7-code`	Moonshot	Agentic coding	$0.72/ 1MPublic ref.~~$0.95~~	$3/ 1MPublic ref.$4
Kimi K2.6`kimi-k2.6`	Moonshot	Long-form reasoning & coding	$0.48/ 1MPublic ref.~~$0.89~~	$2.30/ 1MPublic ref.~~$3.71~~
Qwen3.7-Max`qwen3.7-max`	Alibaba	Complex automation	$1.24/ 1MPublic ref.~~$2.50~~	$3.72/ 1MPublic ref.~~$7.50~~
DeepSeek V4 Pro`deepseek-v4-pro`	DeepSeek	Reasoning and debugging	$0.31/ 1MPublic ref.~~$0.44~~	$0.62/ 1MPublic ref.~~$0.87~~
Qwen3.7-Plus`qwen3.7-plus-2026-05-26`	Alibaba	Multimodal agents	$0.25/ 1MPublic ref.~~$0.40~~	$1.20/ 1MPublic ref.~~$1.60~~
LongCat-2.0`meituan-longcat/LongCat-2.0`	Meituan LongCat	Agentic coding	$1.35/ 1M	$5.40/ 1M
MiniMax M3`minimax-m3`	MiniMax	Long-context product work	$0.55/ 1M	$2.20/ 1M
Qwen3.5-Plus`qwen3.5-plus-2026-04-20`	Alibaba	Production value	$0.28/ 1MPublic ref.~~$0.40~~	$1.55/ 1MPublic ref.~~$2.40~~
Grok 4.5`grok-4.5`	xAI	Reasoning & coding	$1.40/ 1MPublic ref.$2	$4.20/ 1MPublic ref.$6
Grok 4.3`grok-4.3`	xAI	Fast reasoning	$0.88/ 1MPublic ref.~~$1.25~~	$1.75/ 1MPublic ref.~~$2.50~~
Claude Opus 5`claude-opus-5`	Anthropic	Frontier coding & agents	$0.85/ 1MPublic ref.$5	$4.25/ 1MPublic ref.~~$25~~
Claude Opus 4.8`claude-opus-4-8`	Anthropic	Hard coding & long-horizon agents	$3/ 1MPublic ref.$5	$15/ 1MPublic ref.~~$25~~
Claude Sonnet 5`claude-sonnet-5`	Anthropic	Real-time agents & tool use	$1.20/ 1MPublic ref.$2	$6/ 1MPublic ref.~~$10~~
Claude Fable 5`claude-fable-5`	Anthropic	Frontier reasoning	$7/ 1MPublic ref.~~$10~~	$35/ 1MPublic ref.~~$50~~
Claude Opus 4.7`claude-opus-4-7`	Anthropic	Hard coding & agents	$3.50/ 1MPublic ref.$5	$17.5/ 1MPublic ref.~~$25~~
Claude Sonnet 4.6`claude-sonnet-4-6`	Anthropic	Balanced coding & agents	$2.10/ 1MPublic ref.$3	$10.5/ 1MPublic ref.~~$15~~
Claude Haiku 4.5`claude-haiku-4-5-20251001`	Anthropic	Fast, high-volume Claude	$0.50/ 1MPublic ref.$1	$2.50/ 1MPublic ref.$5
Gemini 3.1 Pro`gemini-3.1-pro-preview`	Google	Multimodal reasoning & coding	$1.20/ 1MPublic ref.$2	$7.20/ 1MPublic ref.~~$12~~
Gemini 2.5 Pro`gemini-2.5-pro`	Google	Multimodal reasoning	$0.97/ 1MPublic ref.~~$1.25~~	$7.75/ 1MPublic ref.~~$10~~
Gemini 3.5 Flash`gemini-3.5-flash`	Google	Fast multimodal reasoning	$1.16/ 1MPublic ref.~~$1.50~~	$6.98/ 1MPublic ref.$9
Gemini 2.5 Flash`gemini-2.5-flash`	Google	High-volume multimodal	$0.23/ 1MPublic ref.~~$0.30~~	$1.94/ 1MPublic ref.~~$2.50~~
GPT-5.5`gpt-5.5`	OpenAI	Frontier agentic coding	$3/ 1MPublic ref.$5	$18/ 1MPublic ref.~~$30~~
GPT-5.6 Terra`gpt-5.6-terra`	OpenAI	Balanced frontier + long context	$1.75/ 1MPublic ref.~~$2.50~~	$10.5/ 1MPublic ref.~~$15~~
GPT-5.4`gpt-5.4`	OpenAI	General coding & agents	$1.75/ 1MPublic ref.~~$2.50~~	$10.5/ 1MPublic ref.~~$15~~
GPT-5`gpt-5`	OpenAI	General assistants & coding	$0.90/ 1MPublic ref.~~$1.25~~	$7.20/ 1MPublic ref.~~$10~~
GPT-5 Mini`gpt-5-mini`	OpenAI	Fast, high-volume GPT	$0.20/ 1MPublic ref.~~$0.25~~	$1.60/ 1MPublic ref.$2
GPT Image 2`gpt-image-2`	OpenAI	Posters, packaging & illustration	$2.25/ 1M	$13.5/ 1M
Gemini 2.5 Flash Image`gemini-2.5-flash-image`	Google	Everyday image generation & editing	$0.09/ 1M	$9/ 1M
Gemini 3.1 Flash Image`gemini-3.1-flash-image-preview`	Google	Fast, higher-fidelity images	$0.15/ 1M	$18/ 1M
Seedance 2.0`doubao-seedance-2-0-260128`	ByteDance	Ad, film & social video	$2.32/ 1M	$2.32/ 1M
Seedance 2.0 Fast`doubao-seedance-2-0-fast-260128`	ByteDance	High-volume video generation	$3.20/ 1M	$3.20/ 1M
Seedance 2.0 Mini`doubao-seedance-2-0-mini-260615`	ByteDance	Day-to-day video runs	$2.04/ 1M	$2.04/ 1M
DeepSeek V4 Flash`deepseek-v4-flash-202605`	DeepSeek	Budget · General · Long context	$0.20/ 1M	$0.40/ 1M
GLM-5-Turbo`glm-5-turbo`	Zhipu	Agent · Tool use	$1.50/ 1M	$5.20/ 1M
GLM-5V-Turbo`glm-5v-turbo`	Zhipu	Vision · Coding	$1.60/ 1M	$5.40/ 1M
Kimi K2.7 Code HighSpeed`kimi-k2.7-code-highspeed`	Moonshot	Coding · Fast · Agentic	$0.82/ 1MPublic ref.~~$0.95~~	$3.95/ 1MPublic ref.$4
MiniMax M2.5`minimax-m2.5`	MiniMax	Value · Agents	$0.50/ 1M	$2/ 1M
MiniMax M2.7`minimax-m2.7`	MiniMax	Coding · Productivity	$0.52/ 1M	$2.10/ 1M
Qwen3.5-Flash`qwen3.5-flash`	Alibaba	Ultra-budget · Fast	$0.12/ 1M	$0.95/ 1M
Qwen3.6 Open 27B`qwen3.6-27b`	Alibaba	Open · Advanced	$0.95/ 1M	$4.95/ 1M
Qwen3.6-Flash`qwen3.6-flash`	Alibaba	Fast · Budget · Long context	$0.17/ 1M	$1/ 1M
Qwen3.6-Plus`qwen3.6-plus-2026-04-02`	Alibaba	Compatibility · Multimodal	$0.20/ 1MPublic ref.~~$0.50~~	$1.25/ 1MPublic ref.$3
Qwen3.5-35B-A3B`qwen3.5-35b-a3b`	Alibaba	Fast · Budget · MoE	$0.16/ 1MPublic ref.~~$0.25~~	$1.30/ 1MPublic ref.$2
Claude Opus 4.5`claude-opus-4-5-20251101`	Anthropic	Flagship · Coding · Agents	$3.88/ 1MPublic ref.$5	$19.38/ 1MPublic ref.~~$25~~
Claude Opus 4.5 Thinking`claude-opus-4-5-20251101-thinking`	Anthropic	Flagship · Reasoning · Thinking	$3.88/ 1MPublic ref.$5	$19.38/ 1MPublic ref.~~$25~~
Claude Opus 4.6`claude-opus-4-6`	Anthropic	Flagship · Coding · Agents	$3.88/ 1MPublic ref.$5	$19.38/ 1MPublic ref.~~$25~~
Claude Opus 4.6 Thinking`claude-opus-4-6-thinking`	Anthropic	Flagship · Reasoning · Thinking	$3.88/ 1MPublic ref.$5	$19.38/ 1MPublic ref.~~$25~~
Claude Sonnet 4.5 (0929)`claude-sonnet-4-5-20250929`	Anthropic	Balanced · Coding · Agents	$2.33/ 1MPublic ref.$3	$11.63/ 1MPublic ref.~~$15~~
Claude Sonnet 4.5 Thinking`claude-sonnet-4-5-20250929-thinking`	Anthropic	Balanced · Reasoning · Thinking	$2.33/ 1MPublic ref.$3	$11.63/ 1MPublic ref.~~$15~~
Claude Sonnet 4.6 Thinking`claude-sonnet-4-6-thinking`	Anthropic	Balanced · Reasoning · Thinking	$2.33/ 1MPublic ref.$3	$11.63/ 1MPublic ref.~~$15~~
GPT-4o mini`gpt-4o-mini`	OpenAI	Reasoning · Math	$0.12/ 1MPublic ref.~~$0.15~~	$0.49/ 1MPublic ref.~~$0.60~~
Kimi K2.5`kimi-k2.5`	Moonshot	General · Multimodal	$0.45/ 1MPublic ref.~~$0.57~~	$2/ 1MPublic ref.~~$3.01~~
GLM-5`glm-5`	Zhipu	Agents · Value	$0.54/ 1MPublic ref.$1	$1.74/ 1MPublic ref.~~$3.20~~
GLM-5.1`glm-5.1`	Zhipu	Reasoning · Agents	$0.79/ 1MPublic ref.~~$1.40~~	$2.56/ 1MPublic ref.~~$4.40~~
Gemini 2.5 Flash Lite`gemini-2.5-flash-lite`	Google	Fast · Low cost · Multimodal	$0.08/ 1MPublic ref.~~$0.10~~	$0.31/ 1MPublic ref.~~$0.40~~
Gemini 2.5 Flash Thinking`gemini-2.5-flash-thinking`	Google	Reasoning · Multimodal · Thinking	$0.23/ 1MPublic ref.~~$0.30~~	$1.94/ 1MPublic ref.~~$2.50~~
Gemini 3 Flash (preview)`gemini-3-flash-preview`	Google	Fast · Multimodal · Preview	$0.39/ 1MPublic ref.~~$0.50~~	$2.33/ 1MPublic ref.$3
Gemini 3.1 Flash Lite`gemini-3.1-flash-lite`	Google	Fast · Low cost · Multimodal	$0.19/ 1MPublic ref.~~$0.25~~	$1.16/ 1MPublic ref.~~$1.50~~
Gemini 3.1 Flash Lite (preview)`gemini-3.1-flash-lite-preview`	Google	Fast · Low cost · Preview	$0.19/ 1M	$1.16/ 1M
Gemini 3.1 Pro Thinking`gemini-3.1-pro-preview-thinking`	Google	Reasoning · Multimodal · Thinking	$1.40/ 1MPublic ref.$2	$8.40/ 1MPublic ref.~~$12~~
GPT-5.4 Mini`gpt-5.4-mini`	OpenAI	Fast · Low cost	$0.53/ 1MPublic ref.~~$0.75~~	$3.15/ 1MPublic ref.~~$4.50~~
GPT-5.6 Luna`gpt-5.6-luna`	OpenAI	Frontier · Efficient · Long context	$0.70/ 1MPublic ref.$1	$4.20/ 1MPublic ref.$6
GPT-5.6 Sol`gpt-5.6-sol`	OpenAI	Frontier · Agents · Long context	$3.50/ 1MPublic ref.$5	$21/ 1MPublic ref.~~$30~~

Sell prices may change as upstream prices move. Linked public references open their source in a new tab.