AI API Pricing & Models | Modelflare

Compare AI API prices, billing units and supported endpoints for text, image and video models. Review model groups and request conditions.

Prices are in USD. The listed group rate applies before any request-specific multiplier. Your account may have different access or discounts.

ModelGroupConditionsUnitPrice
MiniMax-H3MediaOutput · 2kPer secondUSD 0.1521
claude-fable-5claude-awardInput · StandardPer 1M tokensUSD 2.5
claude-fable-5claude-first-topupInput · StandardPer 1M tokensUSD 0.3
claude-fable-5claude-premiumInput · StandardPer 1M tokensUSD 5
claude-fable-5claude-stableInput · StandardPer 1M tokensUSD 3.15
claude-fable-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.6
claude-fable-5-1claude-awardInput · StandardPer 1M tokensUSD 2.5
claude-fable-5-1claude-first-topupInput · StandardPer 1M tokensUSD 0.3
claude-fable-5-1claude-premiumInput · StandardPer 1M tokensUSD 5
claude-fable-5-1claude-stableInput · StandardPer 1M tokensUSD 3.15
claude-fable-5-1claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.6
claude-haiku-4-5claude-awardInput · StandardPer 1M tokensUSD 0.25
claude-haiku-4-5claude-first-topupInput · StandardPer 1M tokensUSD 0.03
claude-haiku-4-5claude-premiumInput · StandardPer 1M tokensUSD 0.5
claude-haiku-4-5claude-stableInput · StandardPer 1M tokensUSD 0.315
claude-haiku-4-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.06
claude-haiku-5-5claude-awardInput · Context length <= 100000Per 1M tokensUSD 0.025
claude-haiku-5-5claude-first-topupInput · Context length <= 100000Per 1M tokensUSD 0.003
claude-haiku-5-5claude-premiumInput · Context length <= 100000Per 1M tokensUSD 0.05
claude-haiku-5-5claude-stableInput · Context length <= 100000Per 1M tokensUSD 0.0315
claude-haiku-5-5claude-tmp-cheapInput · Context length <= 100000Per 1M tokensUSD 0.006
claude-opus-4-8claude-awardInput · StandardPer 1M tokensUSD 1.25
claude-opus-4-8claude-first-topupInput · StandardPer 1M tokensUSD 0.15
claude-opus-4-8claude-premiumInput · StandardPer 1M tokensUSD 2.5
claude-opus-4-8claude-stableInput · StandardPer 1M tokensUSD 1.575
claude-opus-4-8claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.3
claude-opus-5claude-awardInput · StandardPer 1M tokensUSD 1.25
claude-opus-5claude-first-topupInput · StandardPer 1M tokensUSD 0.15
claude-opus-5claude-premiumInput · StandardPer 1M tokensUSD 2.5
claude-opus-5claude-stableInput · StandardPer 1M tokensUSD 1.575
claude-opus-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.3
claude-opus-5-5claude-awardInput · StandardPer 1M tokensUSD 1
claude-opus-5-5claude-first-topupInput · StandardPer 1M tokensUSD 0.12
claude-opus-5-5claude-premiumInput · StandardPer 1M tokensUSD 2
claude-opus-5-5claude-stableInput · StandardPer 1M tokensUSD 1.26
claude-opus-5-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.24
claude-sonnet-5claude-awardInput · StandardPer 1M tokensUSD 0.5
claude-sonnet-5claude-first-topupInput · StandardPer 1M tokensUSD 0.06
claude-sonnet-5claude-premiumInput · StandardPer 1M tokensUSD 1
claude-sonnet-5claude-stableInput · StandardPer 1M tokensUSD 0.63
claude-sonnet-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.12
claude-sonnet-5-5claude-awardInput · StandardPer 1M tokensUSD 0.5
claude-sonnet-5-5claude-first-topupInput · StandardPer 1M tokensUSD 0.06
claude-sonnet-5-5claude-premiumInput · StandardPer 1M tokensUSD 1
claude-sonnet-5-5claude-stableInput · StandardPer 1M tokensUSD 0.63
claude-sonnet-5-5claude-tmp-cheapInput · StandardPer 1M tokensUSD 0.12
codex-auto-reviewopenai-awardInput · StandardPer 1M tokensUSD 0.075
codex-auto-reviewopenai-enterpriseInput · StandardPer 1M tokensUSD 1.25
codex-auto-reviewopenai-first-topupInput · StandardPer 1M tokensUSD 0.0375
codex-auto-reviewopenai-premiumInput · StandardPer 1M tokensUSD 0.325
codex-auto-reviewopenai-stableInput · StandardPer 1M tokensUSD 0.2
deepseek-v4-flashdeepseek-awardInput · StandardPer 1M tokensUSD 0.15
deepseek-v4-flashdeepseek-stableInput · StandardPer 1M tokensUSD 0.2571428571428571
deepseek-v4-prodeepseek-awardInput · StandardPer 1M tokensUSD 0.45
deepseek-v4-prodeepseek-stableInput · StandardPer 1M tokensUSD 0.7714285714285715
deepseek-v4.1-flashdeepseek-awardInput · StandardPer 1M tokensUSD 0.1129032258064516
deepseek-v4.1-flashdeepseek-stableInput · StandardPer 1M tokensUSD 0.1935483870967742
gemini-2.5-flash-imageMediaPrice · StandardPer requestUSD 0.032955000000000005
gemini-3-pro-imageMediaInput · StandardPer 1M tokensUSD 1.6900000000000002
gemini-3.1-flash-imageMediaInput · StandardPer 1M tokensUSD 0.42250000000000004
gemini-3.1-flash-litegemini-stableInput · StandardPer 1M tokensUSD 0.0375
gemini-3.1-flash-lite-imageMediaInput · StandardPer 1M tokensUSD 0.21125000000000002
gemini-3.1-pro-previewgemini-stableInput · Context length <= 200000Per 1M tokensUSD 0.3
gemini-3.5-flashgemini-stableInput · StandardPer 1M tokensUSD 0.22499999999999998
gemini-3.5-flash-litegemini-stableInput · StandardPer 1M tokensUSD 0.045
gemini-3.6-flashgemini-stableInput · StandardPer 1M tokensUSD 0.22499999999999998
gemini-3.7-flashgemini-stableInput · StandardPer 1M tokensUSD 0.22499999999999998
gemini-3.8-flashgemini-stableInput · StandardPer 1M tokensUSD 0.22499999999999998
gemini-3.8-flash-highgemini-stableInput · StandardPer 1M tokensUSD 0.22499999999999998
glm-5.2glm-awardInput · StandardPer 1M tokensUSD 0.48999999999999994
glm-5.2glm-stableInput · StandardPer 1M tokensUSD 0.7
glm-5.3glm-awardInput · StandardPer 1M tokensUSD 0.39999999999999997
glm-5.3glm-stableInput · StandardPer 1M tokensUSD 0.5714285714285714
glm-5.3-flashglm-awardInput · StandardPer 1M tokensUSD 0.039999999999999994
glm-5.3-flashglm-stableInput · StandardPer 1M tokensUSD 0.05714285714285714
gpt-5.4openai-awardInput · StandardPer 1M tokensUSD 0.075
gpt-5.4openai-enterpriseInput · StandardPer 1M tokensUSD 1.25
gpt-5.4openai-first-topupInput · StandardPer 1M tokensUSD 0.0375
gpt-5.4openai-premiumInput · StandardPer 1M tokensUSD 0.325
gpt-5.4openai-stableInput · StandardPer 1M tokensUSD 0.2
gpt-5.5openai-awardInput · StandardPer 1M tokensUSD 0.15
gpt-5.5openai-enterpriseInput · StandardPer 1M tokensUSD 2.5
gpt-5.5openai-first-topupInput · StandardPer 1M tokensUSD 0.075
gpt-5.5openai-premiumInput · StandardPer 1M tokensUSD 0.65
gpt-5.5openai-stableInput · StandardPer 1M tokensUSD 0.4
gpt-5.6-solopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.15
gpt-5.6-solopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 2.5
gpt-5.6-solopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.075
gpt-5.6-solopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 0.65
gpt-5.6-solopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.4
gpt-5.6-terraopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.06
gpt-5.6-terraopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 1
gpt-5.6-terraopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.03
gpt-5.6-terraopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 0.26
gpt-5.6-terraopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.16
gpt-6-astraopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.3
gpt-6-astraopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 5
gpt-6-astraopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.15
gpt-6-astraopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 1.3
gpt-6-astraopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.8
gpt-6-lunaopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.0075
gpt-6-lunaopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 0.125
gpt-6-lunaopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.00375
gpt-6-lunaopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 0.0325
gpt-6-lunaopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.02
gpt-6-solopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.06
gpt-6-solopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 1
gpt-6-solopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.03
gpt-6-solopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 0.26
gpt-6-solopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.16
gpt-6.1-solopenai-awardInput · Context length <= 272000Per 1M tokensUSD 0.06
gpt-6.1-solopenai-enterpriseInput · Context length <= 272000Per 1M tokensUSD 1
gpt-6.1-solopenai-first-topupInput · Context length <= 272000Per 1M tokensUSD 0.03
gpt-6.1-solopenai-premiumInput · Context length <= 272000Per 1M tokensUSD 0.26
gpt-6.1-solopenai-stableInput · Context length <= 272000Per 1M tokensUSD 0.16
gpt-image-2MediaInput · StandardPer 1M tokensUSD 3.77
gpt-image-2.5-flareMediaInput · StandardPer 1M tokensUSD 5.33
gpt-image-2.5-sunburstMediaInput · StandardPer 1M tokensUSD 5.33
grok-4.5grok-awardInput · StandardPer 1M tokensUSD 0.02
grok-4.5grok-stableInput · StandardPer 1M tokensUSD 0.22
grok-4.6grok-awardInput · StandardPer 1M tokensUSD 0.02
grok-4.6grok-stableInput · StandardPer 1M tokensUSD 0.22
grok-4.7grok-awardInput · StandardPer 1M tokensUSD 0.02
grok-4.7grok-stableInput · StandardPer 1M tokensUSD 0.22
happyhorse-1.1-i2vMediaOutput · 1080pPer secondUSD 0.1287
happyhorse-1.1-r2vMediaOutput · 1080pPer secondUSD 0.1287
happyhorse-1.1-t2vMediaOutput · 1080pPer secondUSD 0.1287
jev-1.13jev-premiumInput · StandardPer 1M tokensUSD 0.0483
jev-1.13.0jev-premiumInput · StandardPer 1M tokensUSD 0.0483
kimi-k3kimi-awardInput · StandardPer 1M tokensUSD 1
kimi-k3kimi-stableInput · StandardPer 1M tokensUSD 1.8571428571428572
kling-2.5-turboMediaOutput · 1080pPer secondUSD 0.0637
kling-2.6MediaOutput · 1080pPer secondUSD 0.0637
kling-3.0MediaOutput · 1080pPer secondUSD 0.10192
kling-3.0-omniMediaOutput · 1080pPer secondUSD 0.10192
kling-3.0-turboMediaOutput · 1080pPer secondUSD 0.1274
kling-o1MediaOutput · 1080pPer secondUSD 0.10192
muse-spark-1.3spark-premiumInput · StandardPer 1M tokensUSD 1.4375
qwen3.8-maxqwen-stableInput · StandardPer 1M tokensUSD 1.3714285714285714
seedance-2.0MediaOutput · 1080pPer 1M tokensUSD 9.509500000000001
seedance-2.0-fastMediaOutput · 480pPer 1M tokensUSD 3.435714285714286
seedance-2.0-miniMediaOutput · 480pPer 1M tokensUSD 1.7085714285714286
seedance-2.5MediaOutput · 1080pPer 1M tokensUSD 14.4495
seedream-5-0-lite-260128MediaPrice · StandardPer imageUSD 0.033215
wan2.7-i2vMediaOutput · 1080pPer secondUSD 0.11115000000000001
wan2.7-imageMediaPrice · StandardPer requestUSD 0.021192600000000002
wan2.7-image-proMediaPrice · StandardPer requestUSD 0.0529815
wan2.7-r2vMediaOutput · 1080pPer secondUSD 0.11115000000000001
wan2.7-t2vMediaOutput · 1080pPer secondUSD 0.11115000000000001
wan3.0-videoMediaOutput · 1080pPer secondUSD 0.1976
wan3.0-video-primeMediaOutput · 1080pPer secondUSD 0.3094

Pricing and API questions

How do I calculate the cost of a model request?

Choose the model and route, then check the billing unit and conditions. Text models usually list separate USD rates per million input and output tokens. Cache use, context length and request options may change the rate. Usage records show the settled cost of each request.

Why does the same model have several prices?

A model can have several routing groups with different rates and access conditions. Compare the group, supported protocol and any eligibility requirements together. Promotional rates are subject to their stated conditions; your account may have different access or discounts.

How are image and video requests billed?

Billing depends on the model: per image, per second, per request or by tokens. Resolution, quality, duration, audio and reference inputs can affect the charge. Open the model details and API documentation to check the applicable conditions before sending a request.

Do Castaly generations and API requests use the same balance?

Yes. Castaly at castaly.modelflare.dev uses your Modelflare account and wallet for image and video generation. Modelflare provides direct API access, API keys and usage records. Review the selected model and request settings in either entry point.

What should I check after a failed or timed-out request?

Check the request or task status, usage record and balance changes. A client timeout does not by itself confirm that an upstream task stopped. If the status and charge do not match, contact support with the request or task ID; never include your API key.

Can every model use the same API format?

No. Supported endpoints and parameters depend on the model and route. Check the model documentation for the exact model ID, endpoint, required inputs and streaming or polling behavior. A model listing does not mean every protocol or parameter is supported.

claude-first-topup

Exclusive Claude pricing unlocked when any single top-up reaches US$50. Ideal for personal development, feature validation, and light usage.

openai-first-topup

Exclusive pricing unlocked when any single top-up reaches US$20. Ideal for personal development, feature validation, and light usage.