Every plan can use every model listed here. Your plan is a dollar balance; each request costs its input tokens × the model's input price plus its output tokens × the output price (prices per 1M tokens). Official list prices are shown for comparison.
How pricing works
Example: 100,000 input + 20,000 output tokens on a $1.00 / $5.00 model costs $0.10 + $0.10 = $0.20 of your balance.
Claude Fable 5.1
Claude · standard · Anthropic Messages
95% cheaper
Anthropic's most capable model for demanding reasoning and long-running agent tasks.
Context
1M
Max output
128K
Our price / 1M
$0.480 in · $2.40 out
Official / 1M
$10.00 in · $50.00 out
$40 balance ≈
41.7M tokens (3:1 input/output mix)
CodingUnderstands images
Claude Haiku 4.5
Claude · standard · Anthropic Messages
95% cheaper
Anthropic's fastest model for straightforward tasks.
Context
200K
Max output
64K
Our price / 1M
$0.048 in · $0.240 out
Official / 1M
$1.00 in · $5.00 out
$40 balance ≈
416.7M tokens (3:1 input/output mix)
CodingUnderstands images
Claude Opus 5
Claude · standard · Anthropic Messages
95% cheaper
Anthropic's model for complex coding and agent tasks.
Context
1M
Max output
128K
Our price / 1M
$0.240 in · $1.20 out
Official / 1M
$5.00 in · $25.00 out
$40 balance ≈
83.3M tokens (3:1 input/output mix)
CodingUnderstands images
Claude Opus 5.5
Claude · standard · Anthropic Messages
95% cheaper
Anthropic's model for long-running agentic coding and knowledge work.
Context
1M
Max output
128K
Our price / 1M
$0.192 in · $0.960 out
Official / 1M
$4.00 in · $20.00 out
$40 balance ≈
104.2M tokens (3:1 input/output mix)
CodingUnderstands images
Claude Sonnet 5
Claude · standard · Anthropic Messages
95% cheaper
Anthropic's model balancing speed and intelligence.
Context
1M
Max output
128K
Our price / 1M
$0.096 in · $0.480 out
Official / 1M
$2.00 in · $10.00 out
$40 balance ≈
208.3M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 2.5 Flash Image
Gemini · standard · Chat Completions
95% cheaper
Image generation and editing model for text and image prompts.
Context
32.768K
Max output
65.536K
Our price / 1M
$0.013 in · $1.11 out
Official / 1M
$0.280 in · $23.05 out
$40 balance ≈
139.5M tokens (3:1 input/output mix)
Image generationUnderstands images
Gemini 3 Flash Preview
Gemini · standard · Chat Completions
95% cheaper
Fast chat model with a strong balance of speed, capability, and cost.
Context
1M
Max output
65K
Our price / 1M
$0.024 in · $0.144 out
Official / 1M
$0.500 in · $3.00 out
$40 balance ≈
740.7M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3 Pro Image
Gemini · standard · Chat Completions
95% cheaper
Next-generation image generation model with higher quality output.
Context
65.536K
Max output
32.768K
Our price / 1M
$0.096 in · $0.576 out
Official / 1M
$2.00 in · $12.00 out
$40 balance ≈
185.2M tokens (3:1 input/output mix)
Image generationUnderstands images
Gemini 3.1 Flash Image
Gemini · standard · Chat Completions
95% cheaper
Fast image generation and editing model with pro-level quality.
Context
131.072K
Max output
32.768K
Our price / 1M
$0.024 in · $0.144 out
Official / 1M
$0.500 in · $3.00 out
$40 balance ≈
740.7M tokens (3:1 input/output mix)
Image generationUnderstands images
Gemini 3.1 Flash Lite
Gemini · standard · Chat Completions
95% cheaper
Cost-efficient Gemini 3.1 model for high-volume chat and extraction tasks.
Context
1M
Max output
65K
Our price / 1M
$0.012 in · $0.072 out
Official / 1M
$0.250 in · $1.50 out
$40 balance ≈
1.5B tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3.1 Pro Preview
Gemini · standard · Chat Completions
95% cheaper
Latest preview of Google's next-generation reasoning model.
Context
1M
Max output
64K
Our price / 1M
$0.096 in · $0.576 out
Official / 1M
$2.00 in · $12.00 out
$40 balance ≈
185.2M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3.5 Flash
Gemini · standard · Chat Completions
95% cheaper
High-efficiency Gemini 3.5 model for fast coding, reasoning, and agentic workflows.
Context
1M
Max output
64K
Our price / 1M
$0.072 in · $0.432 out
Official / 1M
$1.50 in · $9.00 out
$40 balance ≈
246.9M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3.6 Flash
Gemini · standard · Chat Completions
95% cheaper
Gemini 3.6 Flash model for fast coding, reasoning, and agentic workflows.
Context
1M
Max output
64K
Our price / 1M
$0.036 in · $0.180 out
Official / 1M
$0.750 in · $3.75 out
$40 balance ≈
555.6M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3.7 Flash
Gemini · standard · Chat Completions
95% cheaper
Gemini 3.7 Flash model for fast coding, reasoning, and agentic workflows.
Context
1M
Max output
64K
Our price / 1M
$0.036 in · $0.180 out
Official / 1M
$0.750 in · $3.75 out
$40 balance ≈
555.6M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 3.8 Flash
Gemini · standard · Chat Completions
95% cheaper
Latest-generation Gemini Flash model for fast coding, reasoning, and agentic workflows.
Context
1.048576M
Max output
65.536K
Our price / 1M
$0.036 in · $0.180 out
Official / 1M
$0.750 in · $3.75 out
$40 balance ≈
555.6M tokens (3:1 input/output mix)
CodingUnderstands images
Gemini 4 Argon
Gemini · standard · Chat Completions
95% cheaper
Frontier Gemini model for long-horizon coding, reasoning, and enterprise knowledge work.
Context
1.048576M
Max output
1.048576M
Our price / 1M
$0.096 in · $0.480 out
Official / 1M
$2.00 in · $10.00 out
$40 balance ≈
208.3M tokens (3:1 input/output mix)
CodingUnderstands images
ChatGPT Latest
GPT · standard · Chat Completions
95% cheaper
The ChatGPT model: points to the latest Instant model currently used in ChatGPT, tuned for natural conversational chat.
Context
128K
Max output
16.384K
Our price / 1M
$0.240 in · $1.44 out
Official / 1M
$5.00 in · $30.00 out
$40 balance ≈
74.1M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5 nano
GPT · standard · Chat Completions
95% cheaper
Most compact GPT-5 model for speed and cost efficiency.
Context
400K
Max output
128K
Our price / 1M
$0.0024 in · $0.019 out
Official / 1M
$0.050 in · $0.400 out
$40 balance ≈
6.1B tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.2
GPT · standard · Chat Completions
95% cheaper
OpenAI reasoning model for complex problem-solving tasks.
Context
400K
Max output
128K
Our price / 1M
$0.084 in · $0.672 out
Official / 1M
$1.75 in · $14.00 out
$40 balance ≈
173.2M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.4
GPT · standard · Chat Completions
95% cheaper
Advanced GPT-5.4 reasoning model for complex analysis and code generation.
Context
1.05M
Max output
128K
Our price / 1M
$0.120 in · $0.720 out
Official / 1M
$2.50 in · $15.00 out
$40 balance ≈
148.1M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.4 Mini
GPT · standard · Chat Completions
95% cheaper
Smaller, faster GPT-5.4 variant balancing reasoning quality and cost.
Context
400K
Max output
128K
Our price / 1M
$0.036 in · $0.216 out
Official / 1M
$0.750 in · $4.50 out
$40 balance ≈
493.8M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.4 Nano
GPT · standard · Chat Completions
95% cheaper
Fastest and lowest-cost GPT-5.4 variant for high-volume tasks.
Context
400K
Max output
128K
Our price / 1M
$0.0096 in · $0.060 out
Official / 1M
$0.200 in · $1.25 out
$40 balance ≈
1.8B tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.5
GPT · standard · Chat Completions
95% cheaper
OpenAI's most capable GPT-5.5 model for demanding reasoning and coding tasks.
Context
1M
Max output
128K
Our price / 1M
$0.240 in · $1.44 out
Official / 1M
$5.00 in · $30.00 out
$40 balance ≈
74.1M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.6 Luna
GPT · standard · Chat Completions
95% cheaper
Fast, low-cost GPT-5.6 model for simple or high-volume tasks.
Context
1.05M
Max output
128K
Our price / 1M
$0.0096 in · $0.058 out
Official / 1M
$0.200 in · $1.20 out
$40 balance ≈
1.9B tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.6 Sol
GPT · standard · Chat Completions
95% cheaper
OpenAI's flagship GPT-5.6 model for the hardest reasoning, coding, and agentic tasks.
Context
1.05M
Max output
128K
Our price / 1M
$0.192 in · $0.960 out
Official / 1M
$4.00 in · $20.00 out
$40 balance ≈
104.2M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-5.6 Terra
GPT · standard · Chat Completions
95% cheaper
Balanced GPT-5.6 model for everyday work at lower cost.
Context
1.05M
Max output
128K
Our price / 1M
$0.096 in · $0.576 out
Official / 1M
$2.00 in · $12.00 out
$40 balance ≈
185.2M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-6 Astra
GPT · standard · Chat Completions
95% cheaper
OpenAI's most capable model for complex reasoning, coding, research, and document creation.
Context
1.05M
Max output
128K
Our price / 1M
$0.480 in · $2.40 out
Official / 1M
$10.00 in · $50.00 out
$40 balance ≈
41.7M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-6 Luna
GPT · standard · Chat Completions
95% cheaper
Low-cost GPT-6 model from OpenAI.
Context
1.05M
Max output
128K
Our price / 1M
$0.0048 in · $0.024 out
Official / 1M
$0.100 in · $0.500 out
$40 balance ≈
4.2B tokens (3:1 input/output mix)
CodingUnderstands images
GPT-6 Sol
GPT · standard · Chat Completions
95% cheaper
Mid-tier GPT-6 model from OpenAI.
Context
1.05M
Max output
128K
Our price / 1M
$0.096 in · $0.480 out
Official / 1M
$2.00 in · $10.00 out
$40 balance ≈
208.3M tokens (3:1 input/output mix)
CodingUnderstands images
GPT-6.1 Sol
GPT · standard · Chat Completions
95% cheaper
Near-Astra performance for complex coding and professional work. Use Responses for tool calling; Chat Completions supports requests without tools.