Skip to content

Model Pricing ​

This page lists prices for GPT, Claude, Gemini, and Grok models. Use it to estimate cost before choosing and integrating models.

Pricing Rules ​

Text models are billed by token usage, and image models are billed per image. Unless otherwise stated, prices are in USD; see the tables below for rates and billing tiers.

Token Billing Dimensions ​

Usually split into three types:

TypeDescription
Input TokensUser input tokens
Output TokensModel-generated tokens
Cache TokensContext cache tokens, supported by some models

Billing Rules ​

  • Billed by token usage
  • Image models use 1K / 2K / 4K per-image billing; see each model table
  • Pricing varies by model
  • Input, output, and cache prices are usually different
  • Long-context models may use cache pricing
  • Gemini prices below use Google's Standard real-time paid tier, not Batch, Flex, or Priority pricing

Price Alignment ​

  • ✅ Provider pricing can be complex, and mistakes may happen. If you find one, contact us. Thanks for understanding

OpenAI (GPT Series) ​

Standard — Short context / Long context ​

Prices are in USD per 1M tokens and use OpenAI Standard pricing. Short context and Long context are determined by the request's input token count; above 272K, Long context rates apply to the full request.

Short context≤272K input tokens
ModelInputCached inputCache writesOutput
gpt-6.1-sol$2.00$0.10$2.50$10.00
gpt-6-astra$10.00$1.00$12.50$50.00
gpt-6-sol$2.00$0.20$2.50$10.00
gpt-6-luna$0.10$0.01$0.125$0.50
gpt-5.6-sol$4.00$0.40$5.00$20.00
gpt-5.6-terra$2.00$0.20$2.50$12.00
gpt-5.6-luna$0.20$0.02$0.25$1.20
Long context>272K input tokens
ModelInputCached inputCache writesOutput
gpt-6.1-sol$4.00$0.20$5.00$15.00
gpt-6-astra$20.00$2.00$25.00$75.00
gpt-6-sol$4.00$0.40$5.00$15.00
gpt-6-luna$0.20$0.02$0.25$0.75
gpt-5.6-sol$8.00$0.80$10.00$30.00
gpt-5.6-terra$4.00$0.40$5.00$18.00
gpt-5.6-luna$0.40$0.04$0.50$1.80

GPT-5.6 Sol’s promotional pricing is available at least through 2026-11-21. Cache writes and cached input are priced separately.

Other Text Models (Standard) ​

Model NameInput Price ($/1M tokens)Output Price ($/1M tokens)Cache Read Price ($/1M tokens)
gpt-5.5$5.00$30.00$0.50
gpt-5.4-mini$0.75$4.50$0.075
gpt-5.3-codex-spark$1.75$14.00$0.175

Image Models (Per-Image Billing) ​

Model NameImage SizePrice
gpt-image-2.5-flare1K$0.134 / image
gpt-image-2.5-flare2K$0.201 / image
gpt-image-2.5-flare4K$0.268 / image
gpt-image-2.5-sunburst1K$0.134 / image
gpt-image-2.5-sunburst2K$0.201 / image
gpt-image-2.5-sunburst4K$0.268 / image
gpt-image-2-medium1K$0.134 / image
gpt-image-2-medium2K$0.201 / image
gpt-image-2-medium4K$0.268 / image

GPT Image models cost $0.134 / $0.201 / $0.268 per image for 1K / 2K / 4K, respectively.

Anthropic (Claude Series) ​

Model NameInput Price ($/1M tokens)Output Price ($/1M tokens)Cache Read Price ($/1M tokens)
claude-fable-5-1$10.00$50.00$0.25
claude-fable-5$10.00$50.00$1.00
claude-opus-5-5$4.00$20.00$0.20
claude-opus-5$5.00$25.00$0.50
claude-opus-4-8$5.00$25.00$0.50
claude-opus-4-7$5.00$25.00$0.50
claude-opus-4-6$5.00$25.00$0.50
claude-sonnet-5-5$2.00$10.00$0.20
claude-sonnet-5$2.00$10.00$0.20
claude-sonnet-4-6$3.00$15.00$0.30
claude-haiku-4-5-20251001$1.00$5.00$0.10

Google (Gemini Series) ​

Text Models (Token Billing) ​

Model NameInput Price ($/1M tokens)Output Price ($/1M tokens)Cache Read Price ($/1M tokens)
gemini-3.8-flash$0.75*$3.75*$0.075*
gemini-3.7-flash$0.75*$3.75*$0.075*
gemini-3.6-flash$0.75*$3.75*$0.075*
gemini-3.5-flash$1.50$9.00$0.15
gemini-3.5-flash-lite$0.30$2.50$0.03
gemini-3.1-flash-lite$0.25$1.50$0.025
gemini-3.1-pro-preview$2.00 (≤200K)
$4.00 (>200K)
$12.00 (≤200K)
$18.00 (>200K)
$0.20 (≤200K)
$0.40 (>200K)
gemini-3-flash-preview$0.50$3.00$0.05
gemini-2.5-flash$0.30$2.50$0.03
gemini-2.5-flash-lite$0.10$0.40$0.01
gemini-2.5-pro$1.25 (≤200K)
$2.50 (>200K)
$10.00 (≤200K)
$15.00 (>200K)
$0.125 (≤200K)
$0.25 (>200K)
  • Promotional Standard pricing for gemini-3.6-flash, gemini-3.7-flash, and gemini-3.8-flash through 2026-12-31. Starting 2027-01-01, the input / output / cache-read prices are $1.50 / $7.50 / $0.15.

Cache Read prices exclude cache storage charges. Grounding, Google Search / Maps, and other tool charges are billed separately and are not included in this table.

Image Models (Per-Image Billing) ​

Model Name1K2K4K
gemini-3.1-flash-image$0.201 / image$0.301 / image$0.451 / image
gemini-3.1-flash-image-preview (compatibility alias)$0.201 / image$0.301 / image$0.451 / image
gemini-3.1-flash-lite-image$0.201 / image$0.301 / image$0.451 / image
gemini-3-pro-image$0.201 / image$0.301 / image$0.451 / image
gemini-3-pro-image-preview (compatibility alias)$0.201 / image$0.301 / image$0.451 / image
gemini-2.5-flash-image$0.201 / image$0.301 / image$0.451 / image

Gemini image models cost $0.201 / $0.301 / $0.451 per image for 1K / 2K / 4K, respectively.

Output dimensions determine the 1K / 2K / 4K billing tier; auto or an unrecognized size uses the 2K tier.

⚠️ Gemini image models (names containing -image) support only Google's native protocol POST {base}/v1beta/models/{model}:generateContent. Do not generate images via OpenAI chat/completions — it returns 200 but silently drops the image while still billing output tokens; OpenAI /v1/images/generations only supports gpt-image-*.

xAI (Grok Series) ​

Model NameInput Price ($/1M tokens)Output Price ($/1M tokens)Cache Read Price ($/1M tokens)Context Window
grok-4.5$2.00$6.00$0.30500K
grok-4.3$1.25$2.50$0.201M

Notes ​

  • Some models may require separate access
  • Long-context models may incur extra costs

Updates ​

  • The model list is updated continuously
  • New models are synced when released