Sign In
Live model catalog

GPT API & Claude API Models and Pricing

Compare live GPT API and Claude API model pricing, availability, and compatible endpoints. Access multiple model providers through one CostRouter API key with usage-based billing.

New accounts receive $0.10 in trial credits. Use representative workloads to verify model identity, response quality, and API compatibility before moving to production.

View integration docs
  • One top-up
  • One API Key
  • Every connected model
  • Pay per use
Lower cost. Same requested model.

Supply-chain efficiency lowers costs without changing the requested model. When another route to that model remains available, CostRouter supports route-level failover; provider-wide outages remain outside our control. Eligible CostRouter availability incidents receive service credits under the applicable policy.

Standard groupsApprox. 20% off
AWS, Microsoft Azure, and Google Cloud partner channels
Value groupsApprox. 70–80% off
Aggregated rates from verified compute and API partners
Auto routes through Value groups by default. To use Standard groups, select the corresponding group when creating an API Key.
  • Model integrity, with no silent substitution
  • Route-level failover
  • Latency-aware routing
  • Incident service credits
  • Request-level usage and cost visibility

Enterprise partnerships

For high-volume or business-critical workloads, we tailor official-channel access, volume pricing, and technical support to your model, region, concurrency, and usage requirements.

Formal company-to-company contracts and B2B bank transfers between corporate accounts are supported.

Contact sales

Available AI API Models

Search live GPT API, Claude API, Gemini, DeepSeek, Grok, and Qwen models. Compare token or request pricing, then copy the model ID required by your integration.

Showing 50 of 50 models
50Models7Providers7GroupsUSD · 1M tokens · Calculated with the selected group price multiplier
Claude
claude-fable-5
AnthropicToken-based
Input
$3/ 1M tokens$10/ 1M tokens
Output
$15/ 1M tokens$50/ 1M tokens
Cache read
$0.3/ 1M tokens$1/ 1M tokens
Cache write
$3.75/ 1M tokens$12.5/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-fable-5-thinking
AnthropicToken-based
Input
$3/ 1M tokens$10/ 1M tokens
Output
$15/ 1M tokens$50/ 1M tokens
Cache read
$0.3/ 1M tokens$1/ 1M tokens
Cache write
$3.75/ 1M tokens$12.5/ 1M tokens
Claude ValuedefaultAnthropicChat
Claude
claude-opus-4-6
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
ClaudeClaude ValueAnthropicChat
Claude
claude-opus-4-6-thinking
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-opus-4-7
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
Claude ValuedefaultAnthropicChat
Claude
claude-opus-4-7-thinking
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-opus-4-8
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-opus-4-8-thinking
AnthropicToken-based
Input
$1.5/ 1M tokens$5/ 1M tokens
Output
$7.5/ 1M tokens$25/ 1M tokens
Cache read
$0.15/ 1M tokens$0.5/ 1M tokens
Cache write
$1.875/ 1M tokens$6.25/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-sonnet-4-5
AnthropicToken-based
Input
$0.9/ 1M tokens$3/ 1M tokens
Output
$4.5/ 1M tokens$15/ 1M tokens
Cache read
$0.09/ 1M tokens$0.3/ 1M tokens
Cache write
$1.125/ 1M tokens$3.75/ 1M tokens
ClaudeClaude ValueAnthropicChat
Claude
claude-sonnet-4-5-thinking
AnthropicToken-based
Input
$0.9/ 1M tokens$3/ 1M tokens
Output
$4.5/ 1M tokens$15/ 1M tokens
Cache read
$0.09/ 1M tokens$0.3/ 1M tokens
Cache write
$1.125/ 1M tokens$3.75/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-sonnet-4-6
AnthropicToken-based
Input
$0.9/ 1M tokens$3/ 1M tokens
Output
$4.5/ 1M tokens$15/ 1M tokens
Cache read
$0.09/ 1M tokens$0.3/ 1M tokens
Cache write
$1.125/ 1M tokens$3.75/ 1M tokens
defaultClaudeAnthropicChat
Claude
claude-sonnet-4-6-thinking
AnthropicToken-based
Input
$0.9/ 1M tokens$3/ 1M tokens
Output
$4.5/ 1M tokens$15/ 1M tokens
Cache read
$0.09/ 1M tokens$0.3/ 1M tokens
Cache write
$1.125/ 1M tokens$3.75/ 1M tokens
defaultClaudeAnthropicChat
Gemini
gemini-2.5-flash-image
GooglePer request
Request
$0.04/ request
defaultImageGeminiChat
Gemini
gemini-2.5-flash-lite
GoogleToken-based
Input
$0.06/ 1M tokens$0.3/ 1M tokens
Output
$0.24/ 1M tokens$1.2/ 1M tokens
Cache read
$0.002/ 1M tokens$0.01/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-2.5-flash-nothinking
GoogleToken-based
Input
$0.06/ 1M tokens$0.3/ 1M tokens
Output
$0.5/ 1M tokens$2.5/ 1M tokens
Gemini ValuedefaultGeminiChat
Gemini
gemini-2.5-pro
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
Cache read
$0.025/ 1M tokens$0.125/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-2.5-pro-nothinking
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-2.5-pro-thinking
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
Gemini ValuedefaultGeminiChat
Gemini
gemini-2.5-pro-thinking-128
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-2.5-pro-thinking-2048
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-2.5-pro-thinking-512
GoogleToken-based
Input
$0.25/ 1M tokens$1.25/ 1M tokens
Output
$2/ 1M tokens$10/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-flash-preview
GoogleToken-based
Input
$0.014/ 1M tokens$0.07/ 1M tokens
Output
$0.086/ 1M tokens$0.43/ 1M tokens
Cache read
$0.0014/ 1M tokens$0.007/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-flash-preview-thinking
GoogleToken-based
Input
$0.1/ 1M tokens$0.5/ 1M tokens
Output
$0.6/ 1M tokens$3/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-flash-preview-thinking-high
GoogleToken-based
Input
$0.1/ 1M tokens$0.5/ 1M tokens
Output
$0.6/ 1M tokens$3/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-flash-preview-thinking-low
GoogleToken-based
Input
$0.1/ 1M tokens$0.5/ 1M tokens
Output
$0.6/ 1M tokens$3/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-pro-image-preview
GooglePer request
Request
$0.24/ request
defaultImageGeminiChat
Gemini
gemini-3-pro-image-preview-2k
GooglePer request
Request
$0.24/ request
defaultImageGeminiChat
Gemini
gemini-3-pro-image-preview-4k
GooglePer request
Request
$0.24/ request
defaultImageGeminiChat
Gemini
gemini-3-pro-preview
GoogleToken-based
Input
$0.114/ 1M tokens$0.57/ 1M tokens
Output
$0.686/ 1M tokens$3.43/ 1M tokens
Cache read
$0.0114/ 1M tokens$0.057/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-pro-preview-thinking-128
GoogleToken-based
Input
$1.6/ 1M tokens$2/ 1M tokens
Output
$9.6/ 1M tokens$12/ 1M tokens
GeminidefaultGeminiChat
Gemini
gemini-3-pro-preview-thinking-high
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3-pro-preview-thinking-low
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3.1-flash-image-preview
GooglePer request
Request
$0.151/ request
defaultImageGeminiChat
Gemini
gemini-3.1-pro
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Cache read
$0.04/ 1M tokens$0.2/ 1M tokens
Gemini ValueGeminiChat
Gemini
gemini-3.1-pro-high
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Gemini ValueGeminiChat
Gemini
gemini-3.1-pro-low
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Gemini ValueGeminiChat
Gemini
gemini-3.1-pro-preview
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Cache read
$0.04/ 1M tokens$0.2/ 1M tokens
Gemini ValuedefaultGeminiChat
Gemini
gemini-3.1-pro-preview-high
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Gemini ValueGeminiChat
Gemini
gemini-3.1-pro-preview-low
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
Gemini ValueGeminiChat
Gemini
gemini-3.1-pro-preview-thinking-high
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
defaultGeminiGeminiChat
Gemini
gemini-3.1-pro-preview-thinking-low
GoogleToken-based
Input
$0.4/ 1M tokens$2/ 1M tokens
Output
$2.4/ 1M tokens$12/ 1M tokens
GeminiGemini ValueGeminiChat
Gemini
gemini-3.5-flash
GoogleToken-based
Input
$0.3/ 1M tokens$1.5/ 1M tokens
Output
$1.8/ 1M tokens$9/ 1M tokens
Cache read
$0.03/ 1M tokens$0.15/ 1M tokens
defaultGeminiGeminiChat
OpenAI
gpt-5.4
OpenAIToken-based
Input
$0.5/ 1M tokens$2.5/ 1M tokens
Output
$3/ 1M tokens$15/ 1M tokens
Cache read
$0.05/ 1M tokens$0.25/ 1M tokens
OpenAI ValuedefaultChat
OpenAI
gpt-5.4-mini
OpenAIToken-based
Input
$0.15/ 1M tokens$0.75/ 1M tokens
Output
$0.9/ 1M tokens$4.5/ 1M tokens
Cache read
$0.015/ 1M tokens$0.075/ 1M tokens
defaultOpenAIChat
OpenAI
gpt-5.5
OpenAIToken-based
Input
$1/ 1M tokens$5/ 1M tokens
Output
$6/ 1M tokens$30/ 1M tokens
Cache read
$0.1/ 1M tokens$0.5/ 1M tokens
OpenAI ValuedefaultChat
OpenAI
gpt-5.6-luna
Dynamic pricing
OpenAIToken-based
Input
$0.2/ 1M tokens$1/ 1M tokens
Output
$1.2/ 1M tokens$6/ 1M tokens
Cache read
$0.02/ 1M tokens$0.1/ 1M tokens
Cache write
$0.25/ 1M tokens$1.25/ 1M tokens
OpenAI ValuedefaultChat
OpenAI
gpt-5.6-sol
Dynamic pricing
OpenAIToken-based
Input
$1/ 1M tokens$5/ 1M tokens
Output
$6/ 1M tokens$30/ 1M tokens
Cache read
$0.1/ 1M tokens$0.5/ 1M tokens
Cache write
$1.25/ 1M tokens$6.25/ 1M tokens
OpenAI ValuedefaultChat
OpenAI
gpt-5.6-terra
Dynamic pricing
OpenAIToken-based
Input
$0.5/ 1M tokens$2.5/ 1M tokens
Output
$3/ 1M tokens$15/ 1M tokens
Cache read
$0.05/ 1M tokens$0.25/ 1M tokens
Cache write
$0.625/ 1M tokens$3.125/ 1M tokens
OpenAI ValuedefaultChat
OpenAI
gpt-image-2
OpenAIPer request
Request
$0.05/ request
defaultImageChat
OpenAI
gpt-image-2-vip
OpenAIPer request
Request
$0.11/ request
defaultImageChat
How to read CostRouter pricing

Prices are shown in USD and use the lowest available price multiplier in the selected routing and pricing group. Token models show input and output prices per 1M tokens; per-request models bill per call; dynamic pricing varies with request parameters such as image size, audio duration, cache usage, or pricing tier.

Group price multiplier
Selecting a group shows its available routes and applies its price multiplier to displayed prices.
Model ID
Copy the exact model ID into your SDK or HTTP request body; CostRouter routes the request through one API Key.
Billing type
Compare token-based, per-request, and dynamic pricing before sending production requests.

GPT and Claude API FAQ

Can I access GPT and Claude APIs with one API key?

Yes. One CostRouter API key can access the available GPT, Claude, and other AI models listed in this catalog. Select the required model ID and a compatible endpoint for each request.

How is GPT API and Claude API pricing displayed?

Token-based models show input and output prices per million tokens. Request-based models show a price per request. The final charge depends on the selected model and billing group.

Which API endpoint should I use?

Use one of the compatible endpoints listed for the selected model. The integration documentation provides the CostRouter Base URL and request formats for supported SDKs.

API model index

GPT and Claude Flagship API Models

A concise reference for flagship GPT and Claude model families available through CostRouter. Use the live catalog above to verify model IDs, endpoint compatibility, route availability, and current pricing.

OpenAIgpt-5.5

GPT-5.5 API

Before integration, verify the available GPT-5.5 route, compatible endpoint, and token billing terms in the live catalog above.

OpenAIgpt-5.6

GPT-5.6 API

Confirm the production model ID, supported request format, and current billing details before routing GPT-5.6 traffic.

Anthropicclaude-opus-4-8

Claude Opus 4.8 API

For Anthropic-compatible integrations, verify route availability, endpoint support, and current token pricing in the catalog above.

Anthropicclaude-fable-5

Claude Fable 5 API

Confirm the model ID, compatible endpoint, and current availability before sending Claude Fable 5 production requests.

Contact us

Choose the channel that best matches your request.

Customer supportsupport@costrouter.aiSales inquirysales@costrouter.ai
Contact us
GPT API & Claude API Pricing and Models | CostRouter