Skip to content

The model field guide

Know your models.

Find a model by developer, capability or exact identity. Compare published API prices and see which coding plans include it.

Explore models
Compare published API rates ↓
Developer
Capability
Sort
More filters
Access

83 models · Select up to 4 to compare rates

Layout
Models with published API list prices in US dollars per million tokens, token limits, reasoning support and the number of catalogued plans that include each one. Each model page lists its sources and check dates.
ModelDeveloperInput $/1MOutput $/1MCache read $/1MContext tokensMax output tokensReasoningIncluded in plansReleased
Claude Opus 5.5DeveloperAnthropicInput $/1M$4.00Output $/1M$20.00Cache read $/1M$0.20Context tokens1MMax output tokens128KReasoningYesIncluded in plans21Released
GPT-6.1 SolDeveloperOpenAIInput $/1M$2.00Output $/1M$10.00Cache read $/1M$0.10Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans5Released
Claude Sonnet 5.5DeveloperAnthropicInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens1MMax output tokens128KReasoningYesIncluded in plans23Released
GPT-5.6 TerraDeveloperOpenAIInput $/1M$2.00Output $/1M$12.00Cache read $/1M$0.20Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans22ReleasedNot recorded
Claude Haiku 4.5DeveloperAnthropicInput $/1M$1.00Output $/1M$5.00Cache read $/1M$0.10Context tokens200KMax output tokens64KReasoningYesIncluded in plans15Released
GPT-6 LunaDeveloperOpenAIInput $/1M$0.10Output $/1M$0.50Cache read $/1M$0.01Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans16Released
GLM 5.3DeveloperZ.AI (Zhipu)Input $/1M$1.40Output $/1M$4.40Cache read $/1M$0.26Context tokens1MMax output tokens128KReasoningYesIncluded in plans8ReleasedNot recorded
DeepSeek-V4.1-FlashDeveloperDeepSeekInput $/1M$0.15Output $/1M$0.60Cache read $/1M$0.003Context tokens1MMax output tokens384KReasoningYesIncluded in plans8ReleasedNot recorded
Grok 4.7DeveloperxAIInput $/1M$2.00Output $/1M$6.00Cache read $/1M$0.50Context tokens500KMax output tokensNot publishedReasoningYesIncluded in plans15ReleasedNot recorded
Gemini 3.8 FlashPromoDeveloperGoogleInput $/1M$0.75Output $/1M$3.75Cache read $/1M$0.075Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans16Released
GLM 5.3 FlashDeveloperZ.AI (Zhipu)Input $/1M$0.15Output $/1M$0.50Cache read $/1M$0.03Context tokens1MMax output tokens128KReasoningYesIncluded in plans8ReleasedNot recorded
Kimi K3DeveloperMoonshot AIInput $/1M$3.00Output $/1M$15.00Cache read $/1M$0.30Context tokens1MMax output tokens1.05MReasoningYesIncluded in plans13ReleasedNot recorded
Claude Fable 5.1DeveloperAnthropicInput $/1M$10.00Output $/1M$50.00Cache read $/1M$0.25Context tokens1MMax output tokens128KReasoningYesIncluded in plans13Released
GPT-6 AstraDeveloperOpenAIInput $/1M$10.00Output $/1M$50.00Cache read $/1M$1.00Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans11Released
GPT-5.3-CodexDeveloperOpenAIInput $/1M$1.75Output $/1M$14.00Cache read $/1M$0.175Context tokens400KMax output tokens128KReasoningYesIncluded in plans8ReleasedNot recorded
Qwen3 Coder NextDeveloperAlibaba Cloud (Qwen)Input $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens262KMax output tokensNot publishedReasoningNoIncluded in plans5Released
Qwen 3.8 Omni FlashDeveloperAlibaba Cloud (Qwen)Input $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4ReleasedNot recorded
Qwen 3.8 Max 0902DeveloperAlibaba Cloud (Qwen)Input $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Qwen 3.8 MaxDeveloperAlibaba Cloud (Qwen)Input $/1M$2.00Output $/1M$6.00Cache read $/1M$0.25Context tokens1MMax output tokens131KReasoningYesIncluded in plans7ReleasedNot recorded
Qwen 3.8 FlashDeveloperAlibaba Cloud (Qwen)Input $/1M$0.15Output $/1M$0.47Cache read $/1M$0.016Context tokens1MMax output tokens131KReasoningYesIncluded in plans6ReleasedNot recorded
Qwen 3.8 27BDeveloperAlibaba Cloud (Qwen)Input $/1M$0.50Output $/1M$3.00Cache read $/1M$0.10Context tokens1MMax output tokens131KReasoningYesIncluded in plans4ReleasedNot recorded
Qwen 3.7 PlusDeveloperAlibaba Cloud (Qwen)Input $/1M$0.40Output $/1M$1.60Cache read $/1M$0.08Context tokens1MMax output tokens131KReasoningYesIncluded in plans7ReleasedNot recorded
Qwen 3.7 FlashDeveloperAlibaba Cloud (Qwen)Input $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4ReleasedNot recorded
Qwen 3.6 PlusDeveloperAlibaba Cloud (Qwen)Input $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Amazon Nova 2 LiteDeveloperAmazonInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans0Released
North Mini CodeDeveloperCohereInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningYesIncluded in plans0Released
Command A+DeveloperCohereInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens128KMax output tokens64KReasoningYesIncluded in plans0Released
Composer 2.5DeveloperCursorInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens200KMax output tokensNot publishedReasoningYesIncluded in plans5ReleasedNot recorded
DeepSeek-V4-Pro-0813DeveloperDeepSeekInput $/1M$0.66Output $/1M$1.98Cache read $/1M$0.022Context tokens1MMax output tokens384KReasoningYesIncluded in plans4ReleasedNot recorded
DeepSeek 3.2DeveloperDeepSeekInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans5Released
Nano Banana ProDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensmax input 65.5KMax output tokens32.8KReasoningYesIncluded in plans3ReleasedNot recorded
Gemini 4 ArgonDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokens1MReasoningNot publishedIncluded in plans0Released
Gemini 3.7 FlashPromoDeveloperGoogleInput $/1M$0.75Output $/1M$3.75Cache read $/1M$0.075Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans11Released
Gemini 3.6 FlashPromoDeveloperGoogleInput $/1M$0.75Output $/1M$3.75Cache read $/1M$0.075Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans6Released
Gemini 3.5 Flash LiteDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans3Released
Gemini 3.5 FlashDeveloperGoogleInput $/1M$1.50Output $/1M$9.00Cache read $/1M$0.15Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans3Released
Gemini 3.1 ProDeveloperGoogleInput $/1M$2.00Output $/1M$12.00Cache read $/1M$0.20Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans8ReleasedNot recorded
Gemini 3.1 Flash LiteDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans3Released
Gemini 3 ProDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans3ReleasedNot recorded
Gemini 3 Flash-LiteDeveloperGoogleInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans3ReleasedNot recorded
Gemini 3 FlashDeveloperGoogleInput $/1M$0.50Output $/1M$3.00Cache read $/1M$0.05Context tokensmax input 1.05MMax output tokens65.5KReasoningYesIncluded in plans3ReleasedNot recorded
LongCat 2.0PromoDeveloperMeituanInput $/1M$0.30Output $/1M$1.20Cache read $/1M$0.006Context tokens1MMax output tokensNot publishedReasoningYesIncluded in plans6Released
Muse Spark 1.3DeveloperMetaInput $/1M$1.25Output $/1M$4.25Cache read $/1M$0.15Context tokens1.05MMax output tokensNot publishedReasoningYesIncluded in plans12ReleasedNot recorded
Muse Spark 1.2DeveloperMetaInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens1.05MMax output tokensNot publishedReasoningYesIncluded in plans6Released
Muse Spark 1.1DeveloperMetaInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens1.05MMax output tokensNot publishedReasoningYesIncluded in plans3Released
Llama 4 ScoutDeveloperMetaInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans0Released
Llama 4 MaverickDeveloperMetaInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans0Released
MAI-Code-1.1-FlashDeveloperMicrosoft AIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans5ReleasedNot recorded
MiniMax M3PromoDeveloperMiniMaxInput $/1M$0.30Output $/1M$1.20Cache read $/1M$0.06Context tokens1MMax output tokens524KReasoningYesIncluded in plans8ReleasedNot recorded
MiniMax M2.7DeveloperMiniMaxInput $/1M$0.30Output $/1M$1.20Cache read $/1M$0.06Context tokens205KMax output tokens205KReasoningYesIncluded in plans7Released
Mistral Large 3DeveloperMistral AIInput $/1M$0.50Output $/1M$1.50Cache read $/1M$0.05Context tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans1Released
Kimi K2.7 CodeDeveloperMoonshot AIInput $/1M$0.95Output $/1M$4.00Cache read $/1M$0.19Context tokens256KMax output tokensNot publishedReasoningYesIncluded in plans7ReleasedNot recorded
Kimi K2.6DeveloperMoonshot AIInput $/1M$0.95Output $/1M$4.00Cache read $/1M$0.16Context tokens262KMax output tokensNot publishedReasoningYesIncluded in plans7ReleasedNot recorded
Kimi K2.5DeveloperMoonshot AIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Nemotron 3 UltraDeveloperNVIDIAInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens1MMax output tokensNot publishedReasoningYesIncluded in plans5Released
Nemotron 3 SuperDeveloperNVIDIAInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans1Released
Nemotron 3 NanoDeveloperNVIDIAInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans1Released
GPT-OSS 120BDeveloperOpenAIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens131KMax output tokens131KReasoningYesIncluded in plans4Released
GPT-OSS 20BDeveloperOpenAIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokens131KMax output tokens131KReasoningYesIncluded in plans1Released
GPT-6 SolDeveloperOpenAIInput $/1M$2.00Output $/1M$10.00Cache read $/1M$0.20Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans12Released
GPT-5.6 Sol ProDeveloperOpenAIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans3ReleasedNot recorded
GPT-5.6 SolPromoDeveloperOpenAIInput $/1M$4.00Output $/1M$20.00Cache read $/1M$0.40Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans21ReleasedNot recorded
GPT-5.6 LunaDeveloperOpenAIInput $/1M$0.20Output $/1M$1.20Cache read $/1M$0.02Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans25ReleasedNot recorded
GPT-5.5DeveloperOpenAIInput $/1M$5.00Output $/1M$30.00Cache read $/1M$0.50Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans7ReleasedNot recorded
GPT-5.4 nanoDeveloperOpenAIInput $/1M$0.20Output $/1M$1.25Cache read $/1M$0.02Context tokens400KMax output tokens128KReasoningYesIncluded in plans1ReleasedNot recorded
GPT-5.4 miniDeveloperOpenAIInput $/1M$0.75Output $/1M$4.50Cache read $/1M$0.075Context tokens400KMax output tokens128KReasoningYesIncluded in plans8ReleasedNot recorded
GPT-5.4DeveloperOpenAIInput $/1M$2.50Output $/1M$15.00Cache read $/1M$0.25Context tokens1.05MMax output tokens128KReasoningYesIncluded in plans8ReleasedNot recorded
GPT-5 Thinking MiniDeveloperOpenAIInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans0ReleasedNot recorded
GPT-5 miniDeveloperOpenAIInput $/1M$0.25Output $/1M$2.00Cache read $/1M$0.025Context tokens400KMax output tokens128KReasoningYesIncluded in plans5ReleasedNot recorded
Laguna S 2.1DeveloperPoolsideInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Step 3.7 FlashDeveloperStepFunInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Step 3.5 FlashDeveloperStepFunInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4ReleasedNot recorded
Tencent Hy3DeveloperTencentInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans6Released
Inkling SmallDeveloperThinking Machines LabInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
InklingDeveloperThinking Machines LabInput $/1MNot publishedOutput $/1MNot publishedCache read $/1MNot publishedContext tokensNot publishedMax output tokensNot publishedReasoningNot publishedIncluded in plans4Released
Grok 4.6DeveloperxAIInput $/1M$2.00Output $/1M$6.00Cache read $/1M$0.50Context tokens500KMax output tokensNot publishedReasoningYesIncluded in plans15ReleasedNot recorded
Grok 4.5DeveloperxAIInput $/1M$2.00Output $/1M$6.00Cache read $/1M$0.30Context tokens500KMax output tokensNot publishedReasoningYesIncluded in plans14ReleasedNot recorded
MiMo V2.6 ProDeveloperXiaomiInput $/1M$0.435Output $/1M$0.87Cache read $/1M$0.0036Context tokens1MMax output tokens128KReasoningYesIncluded in plans6Released
MiMo V2.6 FlashDeveloperXiaomiInput $/1M$0.14Output $/1M$0.28Cache read $/1M$0.0028Context tokens1MMax output tokens128KReasoningYesIncluded in plans6Released
GLM 5.3 FlashXDeveloperZ.AI (Zhipu)Input $/1M$0.37Output $/1M$1.25Cache read $/1M$0.075Context tokens1MMax output tokens128KReasoningYesIncluded in plans4ReleasedNot recorded
GLM 5.2DeveloperZ.AI (Zhipu)Input $/1M$1.40Output $/1M$4.40Cache read $/1M$0.26Context tokens1MMax output tokens128KReasoningYesIncluded in plans7Released
GLM 5.1DeveloperZ.AI (Zhipu)Input $/1M$1.40Output $/1M$4.40Cache read $/1M$0.26Context tokens200KMax output tokens128KReasoningYesIncluded in plans4Released
GLM 5DeveloperZ.AI (Zhipu)Input $/1M$1.00Output $/1M$3.20Cache read $/1M$0.20Context tokens200KMax output tokens128KReasoningYesIncluded in plans9Released

Z.AI (Zhipu)

1M context · Reasoning · Tool calling

Base API rate · USD / 1M tokens

Input $/1M

$1.40

Output $/1M

$4.40

Cache read $/1M

$0.26

xAI

500K context · Reasoning · Tool calling

Base API rate · USD / 1M tokens

Input $/1M

$2.00

Output $/1M

$6.00

Cache read $/1M

$0.50

Moonshot AI

1M context · Reasoning · Tool calling

Base API rate · USD / 1M tokens

Input $/1M

$3.00

Output $/1M

$15.00

Cache read $/1M

$0.30

Published API ratesUSD per million tokens

Shorter bar = lower output price

Claude & OpenAI · higher-priced pairs first

Shared scale: $0 to $50

About these prices & pairings

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.