Base API rate · USD / 1M tokens
Input $/1M
$4.00
Output $/1M
$20.00
Cache read $/1M
$0.20
Published API · In 21 plans
Explore modelThe model field guide
Find a model by developer, capability or exact identity. Compare published API prices and see which coding plans include it.
83 models · Select up to 4 to compare rates
| Model | Developer | Input $/1M | Output $/1M | Cache read $/1M | Context tokens | Max output tokens | Reasoning | Included in plans | Released |
|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 | DeveloperAnthropic | Input $/1M$4.00 | Output $/1M$20.00 | Cache read $/1M$0.20 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans21 | Released |
| GPT-6.1 Sol | DeveloperOpenAI | Input $/1M$2.00 | Output $/1M$10.00 | Cache read $/1M$0.10 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans5 | Released |
| Claude Sonnet 5.5 | DeveloperAnthropic | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans23 | Released |
| GPT-5.6 Terra | DeveloperOpenAI | Input $/1M$2.00 | Output $/1M$12.00 | Cache read $/1M$0.20 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans22 | ReleasedNot recorded |
| Claude Haiku 4.5 | DeveloperAnthropic | Input $/1M$1.00 | Output $/1M$5.00 | Cache read $/1M$0.10 | Context tokens200K | Max output tokens64K | ReasoningYes | Included in plans15 | Released |
| GPT-6 Luna | DeveloperOpenAI | Input $/1M$0.10 | Output $/1M$0.50 | Cache read $/1M$0.01 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans16 | Released |
| GLM 5.3 | DeveloperZ.AI (Zhipu) | Input $/1M$1.40 | Output $/1M$4.40 | Cache read $/1M$0.26 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| DeepSeek-V4.1-Flash | DeveloperDeepSeek | Input $/1M$0.15 | Output $/1M$0.60 | Cache read $/1M$0.003 | Context tokens1M | Max output tokens384K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| Grok 4.7 | DeveloperxAI | Input $/1M$2.00 | Output $/1M$6.00 | Cache read $/1M$0.50 | Context tokens500K | Max output tokensNot published | ReasoningYes | Included in plans15 | ReleasedNot recorded |
| Gemini 3.8 FlashPromo | DeveloperGoogle | Input $/1M$0.75 | Output $/1M$3.75 | Cache read $/1M$0.075 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans16 | Released |
| GLM 5.3 Flash | DeveloperZ.AI (Zhipu) | Input $/1M$0.15 | Output $/1M$0.50 | Cache read $/1M$0.03 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| Kimi K3 | DeveloperMoonshot AI | Input $/1M$3.00 | Output $/1M$15.00 | Cache read $/1M$0.30 | Context tokens1M | Max output tokens1.05M | ReasoningYes | Included in plans13 | ReleasedNot recorded |
| Claude Fable 5.1 | DeveloperAnthropic | Input $/1M$10.00 | Output $/1M$50.00 | Cache read $/1M$0.25 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans13 | Released |
| GPT-6 Astra | DeveloperOpenAI | Input $/1M$10.00 | Output $/1M$50.00 | Cache read $/1M$1.00 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans11 | Released |
| GPT-5.3-Codex | DeveloperOpenAI | Input $/1M$1.75 | Output $/1M$14.00 | Cache read $/1M$0.175 | Context tokens400K | Max output tokens128K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| Qwen3 Coder Next | DeveloperAlibaba Cloud (Qwen) | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens262K | Max output tokensNot published | ReasoningNo | Included in plans5 | Released |
| Qwen 3.8 Omni Flash | DeveloperAlibaba Cloud (Qwen) | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | ReleasedNot recorded |
| Qwen 3.8 Max 0902 | DeveloperAlibaba Cloud (Qwen) | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Qwen 3.8 Max | DeveloperAlibaba Cloud (Qwen) | Input $/1M$2.00 | Output $/1M$6.00 | Cache read $/1M$0.25 | Context tokens1M | Max output tokens131K | ReasoningYes | Included in plans7 | ReleasedNot recorded |
| Qwen 3.8 Flash | DeveloperAlibaba Cloud (Qwen) | Input $/1M$0.15 | Output $/1M$0.47 | Cache read $/1M$0.016 | Context tokens1M | Max output tokens131K | ReasoningYes | Included in plans6 | ReleasedNot recorded |
| Qwen 3.8 27B | DeveloperAlibaba Cloud (Qwen) | Input $/1M$0.50 | Output $/1M$3.00 | Cache read $/1M$0.10 | Context tokens1M | Max output tokens131K | ReasoningYes | Included in plans4 | ReleasedNot recorded |
| Qwen 3.7 Plus | DeveloperAlibaba Cloud (Qwen) | Input $/1M$0.40 | Output $/1M$1.60 | Cache read $/1M$0.08 | Context tokens1M | Max output tokens131K | ReasoningYes | Included in plans7 | ReleasedNot recorded |
| Qwen 3.7 Flash | DeveloperAlibaba Cloud (Qwen) | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | ReleasedNot recorded |
| Qwen 3.6 Plus | DeveloperAlibaba Cloud (Qwen) | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Amazon Nova 2 Lite | DeveloperAmazon | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans0 | Released |
| North Mini Code | DeveloperCohere | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningYes | Included in plans0 | Released |
| Command A+ | DeveloperCohere | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens128K | Max output tokens64K | ReasoningYes | Included in plans0 | Released |
| Composer 2.5 | DeveloperCursor | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens200K | Max output tokensNot published | ReasoningYes | Included in plans5 | ReleasedNot recorded |
| DeepSeek-V4-Pro-0813 | DeveloperDeepSeek | Input $/1M$0.66 | Output $/1M$1.98 | Cache read $/1M$0.022 | Context tokens1M | Max output tokens384K | ReasoningYes | Included in plans4 | ReleasedNot recorded |
| DeepSeek 3.2 | DeveloperDeepSeek | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans5 | Released |
| Nano Banana Pro | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensmax input 65.5K | Max output tokens32.8K | ReasoningYes | Included in plans3 | ReleasedNot recorded |
| Gemini 4 Argon | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokens1M | ReasoningNot published | Included in plans0 | Released |
| Gemini 3.7 FlashPromo | DeveloperGoogle | Input $/1M$0.75 | Output $/1M$3.75 | Cache read $/1M$0.075 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans11 | Released |
| Gemini 3.6 FlashPromo | DeveloperGoogle | Input $/1M$0.75 | Output $/1M$3.75 | Cache read $/1M$0.075 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans6 | Released |
| Gemini 3.5 Flash Lite | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans3 | Released |
| Gemini 3.5 Flash | DeveloperGoogle | Input $/1M$1.50 | Output $/1M$9.00 | Cache read $/1M$0.15 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans3 | Released |
| Gemini 3.1 Pro | DeveloperGoogle | Input $/1M$2.00 | Output $/1M$12.00 | Cache read $/1M$0.20 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| Gemini 3.1 Flash Lite | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans3 | Released |
| Gemini 3 Pro | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans3 | ReleasedNot recorded |
| Gemini 3 Flash-Lite | DeveloperGoogle | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans3 | ReleasedNot recorded |
| Gemini 3 Flash | DeveloperGoogle | Input $/1M$0.50 | Output $/1M$3.00 | Cache read $/1M$0.05 | Context tokensmax input 1.05M | Max output tokens65.5K | ReasoningYes | Included in plans3 | ReleasedNot recorded |
| LongCat 2.0Promo | DeveloperMeituan | Input $/1M$0.30 | Output $/1M$1.20 | Cache read $/1M$0.006 | Context tokens1M | Max output tokensNot published | ReasoningYes | Included in plans6 | Released |
| Muse Spark 1.3 | DeveloperMeta | Input $/1M$1.25 | Output $/1M$4.25 | Cache read $/1M$0.15 | Context tokens1.05M | Max output tokensNot published | ReasoningYes | Included in plans12 | ReleasedNot recorded |
| Muse Spark 1.2 | DeveloperMeta | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens1.05M | Max output tokensNot published | ReasoningYes | Included in plans6 | Released |
| Muse Spark 1.1 | DeveloperMeta | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens1.05M | Max output tokensNot published | ReasoningYes | Included in plans3 | Released |
| Llama 4 Scout | DeveloperMeta | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans0 | Released |
| Llama 4 Maverick | DeveloperMeta | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans0 | Released |
| MAI-Code-1.1-Flash | DeveloperMicrosoft AI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans5 | ReleasedNot recorded |
| MiniMax M3Promo | DeveloperMiniMax | Input $/1M$0.30 | Output $/1M$1.20 | Cache read $/1M$0.06 | Context tokens1M | Max output tokens524K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| MiniMax M2.7 | DeveloperMiniMax | Input $/1M$0.30 | Output $/1M$1.20 | Cache read $/1M$0.06 | Context tokens205K | Max output tokens205K | ReasoningYes | Included in plans7 | Released |
| Mistral Large 3 | DeveloperMistral AI | Input $/1M$0.50 | Output $/1M$1.50 | Cache read $/1M$0.05 | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans1 | Released |
| Kimi K2.7 Code | DeveloperMoonshot AI | Input $/1M$0.95 | Output $/1M$4.00 | Cache read $/1M$0.19 | Context tokens256K | Max output tokensNot published | ReasoningYes | Included in plans7 | ReleasedNot recorded |
| Kimi K2.6 | DeveloperMoonshot AI | Input $/1M$0.95 | Output $/1M$4.00 | Cache read $/1M$0.16 | Context tokens262K | Max output tokensNot published | ReasoningYes | Included in plans7 | ReleasedNot recorded |
| Kimi K2.5 | DeveloperMoonshot AI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Nemotron 3 Ultra | DeveloperNVIDIA | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens1M | Max output tokensNot published | ReasoningYes | Included in plans5 | Released |
| Nemotron 3 Super | DeveloperNVIDIA | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans1 | Released |
| Nemotron 3 Nano | DeveloperNVIDIA | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans1 | Released |
| GPT-OSS 120B | DeveloperOpenAI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens131K | Max output tokens131K | ReasoningYes | Included in plans4 | Released |
| GPT-OSS 20B | DeveloperOpenAI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokens131K | Max output tokens131K | ReasoningYes | Included in plans1 | Released |
| GPT-6 Sol | DeveloperOpenAI | Input $/1M$2.00 | Output $/1M$10.00 | Cache read $/1M$0.20 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans12 | Released |
| GPT-5.6 Sol Pro | DeveloperOpenAI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans3 | ReleasedNot recorded |
| GPT-5.6 SolPromo | DeveloperOpenAI | Input $/1M$4.00 | Output $/1M$20.00 | Cache read $/1M$0.40 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans21 | ReleasedNot recorded |
| GPT-5.6 Luna | DeveloperOpenAI | Input $/1M$0.20 | Output $/1M$1.20 | Cache read $/1M$0.02 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans25 | ReleasedNot recorded |
| GPT-5.5 | DeveloperOpenAI | Input $/1M$5.00 | Output $/1M$30.00 | Cache read $/1M$0.50 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans7 | ReleasedNot recorded |
| GPT-5.4 nano | DeveloperOpenAI | Input $/1M$0.20 | Output $/1M$1.25 | Cache read $/1M$0.02 | Context tokens400K | Max output tokens128K | ReasoningYes | Included in plans1 | ReleasedNot recorded |
| GPT-5.4 mini | DeveloperOpenAI | Input $/1M$0.75 | Output $/1M$4.50 | Cache read $/1M$0.075 | Context tokens400K | Max output tokens128K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| GPT-5.4 | DeveloperOpenAI | Input $/1M$2.50 | Output $/1M$15.00 | Cache read $/1M$0.25 | Context tokens1.05M | Max output tokens128K | ReasoningYes | Included in plans8 | ReleasedNot recorded |
| GPT-5 Thinking Mini | DeveloperOpenAI | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans0 | ReleasedNot recorded |
| GPT-5 mini | DeveloperOpenAI | Input $/1M$0.25 | Output $/1M$2.00 | Cache read $/1M$0.025 | Context tokens400K | Max output tokens128K | ReasoningYes | Included in plans5 | ReleasedNot recorded |
| Laguna S 2.1 | DeveloperPoolside | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Step 3.7 Flash | DeveloperStepFun | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Step 3.5 Flash | DeveloperStepFun | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | ReleasedNot recorded |
| Tencent Hy3 | DeveloperTencent | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans6 | Released |
| Inkling Small | DeveloperThinking Machines Lab | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Inkling | DeveloperThinking Machines Lab | Input $/1MNot published | Output $/1MNot published | Cache read $/1MNot published | Context tokensNot published | Max output tokensNot published | ReasoningNot published | Included in plans4 | Released |
| Grok 4.6 | DeveloperxAI | Input $/1M$2.00 | Output $/1M$6.00 | Cache read $/1M$0.50 | Context tokens500K | Max output tokensNot published | ReasoningYes | Included in plans15 | ReleasedNot recorded |
| Grok 4.5 | DeveloperxAI | Input $/1M$2.00 | Output $/1M$6.00 | Cache read $/1M$0.30 | Context tokens500K | Max output tokensNot published | ReasoningYes | Included in plans14 | ReleasedNot recorded |
| MiMo V2.6 Pro | DeveloperXiaomi | Input $/1M$0.435 | Output $/1M$0.87 | Cache read $/1M$0.0036 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans6 | Released |
| MiMo V2.6 Flash | DeveloperXiaomi | Input $/1M$0.14 | Output $/1M$0.28 | Cache read $/1M$0.0028 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans6 | Released |
| GLM 5.3 FlashX | DeveloperZ.AI (Zhipu) | Input $/1M$0.37 | Output $/1M$1.25 | Cache read $/1M$0.075 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans4 | ReleasedNot recorded |
| GLM 5.2 | DeveloperZ.AI (Zhipu) | Input $/1M$1.40 | Output $/1M$4.40 | Cache read $/1M$0.26 | Context tokens1M | Max output tokens128K | ReasoningYes | Included in plans7 | Released |
| GLM 5.1 | DeveloperZ.AI (Zhipu) | Input $/1M$1.40 | Output $/1M$4.40 | Cache read $/1M$0.26 | Context tokens200K | Max output tokens128K | ReasoningYes | Included in plans4 | Released |
| GLM 5 | DeveloperZ.AI (Zhipu) | Input $/1M$1.00 | Output $/1M$3.20 | Cache read $/1M$0.20 | Context tokens200K | Max output tokens128K | ReasoningYes | Included in plans9 | Released |
Base API rate · USD / 1M tokens
Input $/1M
$4.00
Output $/1M
$20.00
Cache read $/1M
$0.20
Published API · In 21 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$2.00
Output $/1M
$10.00
Cache read $/1M
$0.10
Published API · In 5 plans
Explore modelPricing context
See available plans and provider pricing details.
Published API · In 23 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$2.00
Output $/1M
$12.00
Cache read $/1M
$0.20
Published API · In 22 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$1.00
Output $/1M
$5.00
Cache read $/1M
$0.10
Published API · In 15 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$0.10
Output $/1M
$0.50
Cache read $/1M
$0.01
Published API · In 16 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$1.40
Output $/1M
$4.40
Cache read $/1M
$0.26
Published API · In 8 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$0.15
Output $/1M
$0.60
Cache read $/1M
$0.003
Published API · In 8 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$2.00
Output $/1M
$6.00
Cache read $/1M
$0.50
Published API · In 15 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$0.75
Output $/1M
$3.75
Cache read $/1M
$0.075
Published API · In 16 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$0.15
Output $/1M
$0.50
Cache read $/1M
$0.03
Published API · In 8 plans
Explore modelBase API rate · USD / 1M tokens
Input $/1M
$3.00
Output $/1M
$15.00
Cache read $/1M
$0.30
Published API · In 13 plans
Explore modelShorter bar = lower output price
Claude & OpenAI · higher-priced pairs first
Shared scale: $0 to $50
Bars show the selected token price on one shared scale. Pair rows are ordered by the higher price in each pair. Pairings are editorial comparisons, not claims of equal capability or measured popularity.
Current published base rates; context tiers, time-based rates and cache-write duration can change the price. Inspect each model for conditions and sources. Missing rates are not zero.