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.
| Model | Group | Conditions | Unit | Price |
|---|---|---|---|---|
| MiniMax-H3 | Media | Output · 2k | Per second | USD 0.1521 |
| claude-fable-5 | claude-award | Input · Standard | Per 1M tokens | USD 2.5 |
| claude-fable-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.3 |
| claude-fable-5 | claude-premium | Input · Standard | Per 1M tokens | USD 5 |
| claude-fable-5 | claude-stable | Input · Standard | Per 1M tokens | USD 3.15 |
| claude-fable-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.6 |
| claude-fable-5-1 | claude-award | Input · Standard | Per 1M tokens | USD 2.5 |
| claude-fable-5-1 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.3 |
| claude-fable-5-1 | claude-premium | Input · Standard | Per 1M tokens | USD 5 |
| claude-fable-5-1 | claude-stable | Input · Standard | Per 1M tokens | USD 3.15 |
| claude-fable-5-1 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.6 |
| claude-haiku-4-5 | claude-award | Input · Standard | Per 1M tokens | USD 0.25 |
| claude-haiku-4-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.03 |
| claude-haiku-4-5 | claude-premium | Input · Standard | Per 1M tokens | USD 0.5 |
| claude-haiku-4-5 | claude-stable | Input · Standard | Per 1M tokens | USD 0.315 |
| claude-haiku-4-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.06 |
| claude-haiku-5-5 | claude-award | Input · Context length <= 100000 | Per 1M tokens | USD 0.025 |
| claude-haiku-5-5 | claude-first-topup | Input · Context length <= 100000 | Per 1M tokens | USD 0.003 |
| claude-haiku-5-5 | claude-premium | Input · Context length <= 100000 | Per 1M tokens | USD 0.05 |
| claude-haiku-5-5 | claude-stable | Input · Context length <= 100000 | Per 1M tokens | USD 0.0315 |
| claude-haiku-5-5 | claude-tmp-cheap | Input · Context length <= 100000 | Per 1M tokens | USD 0.006 |
| claude-opus-4-8 | claude-award | Input · Standard | Per 1M tokens | USD 1.25 |
| claude-opus-4-8 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.15 |
| claude-opus-4-8 | claude-premium | Input · Standard | Per 1M tokens | USD 2.5 |
| claude-opus-4-8 | claude-stable | Input · Standard | Per 1M tokens | USD 1.575 |
| claude-opus-4-8 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.3 |
| claude-opus-5 | claude-award | Input · Standard | Per 1M tokens | USD 1.25 |
| claude-opus-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.15 |
| claude-opus-5 | claude-premium | Input · Standard | Per 1M tokens | USD 2.5 |
| claude-opus-5 | claude-stable | Input · Standard | Per 1M tokens | USD 1.575 |
| claude-opus-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.3 |
| claude-opus-5-5 | claude-award | Input · Standard | Per 1M tokens | USD 1 |
| claude-opus-5-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.12 |
| claude-opus-5-5 | claude-premium | Input · Standard | Per 1M tokens | USD 2 |
| claude-opus-5-5 | claude-stable | Input · Standard | Per 1M tokens | USD 1.26 |
| claude-opus-5-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.24 |
| claude-sonnet-5 | claude-award | Input · Standard | Per 1M tokens | USD 0.5 |
| claude-sonnet-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.06 |
| claude-sonnet-5 | claude-premium | Input · Standard | Per 1M tokens | USD 1 |
| claude-sonnet-5 | claude-stable | Input · Standard | Per 1M tokens | USD 0.63 |
| claude-sonnet-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.12 |
| claude-sonnet-5-5 | claude-award | Input · Standard | Per 1M tokens | USD 0.5 |
| claude-sonnet-5-5 | claude-first-topup | Input · Standard | Per 1M tokens | USD 0.06 |
| claude-sonnet-5-5 | claude-premium | Input · Standard | Per 1M tokens | USD 1 |
| claude-sonnet-5-5 | claude-stable | Input · Standard | Per 1M tokens | USD 0.63 |
| claude-sonnet-5-5 | claude-tmp-cheap | Input · Standard | Per 1M tokens | USD 0.12 |
| codex-auto-review | openai-award | Input · Standard | Per 1M tokens | USD 0.075 |
| codex-auto-review | openai-enterprise | Input · Standard | Per 1M tokens | USD 1.25 |
| codex-auto-review | openai-first-topup | Input · Standard | Per 1M tokens | USD 0.0375 |
| codex-auto-review | openai-premium | Input · Standard | Per 1M tokens | USD 0.325 |
| codex-auto-review | openai-stable | Input · Standard | Per 1M tokens | USD 0.2 |
| deepseek-v4-flash | deepseek-award | Input · Standard | Per 1M tokens | USD 0.15 |
| deepseek-v4-flash | deepseek-stable | Input · Standard | Per 1M tokens | USD 0.2571428571428571 |
| deepseek-v4-pro | deepseek-award | Input · Standard | Per 1M tokens | USD 0.45 |
| deepseek-v4-pro | deepseek-stable | Input · Standard | Per 1M tokens | USD 0.7714285714285715 |
| deepseek-v4.1-flash | deepseek-award | Input · Standard | Per 1M tokens | USD 0.1129032258064516 |
| deepseek-v4.1-flash | deepseek-stable | Input · Standard | Per 1M tokens | USD 0.1935483870967742 |
| gemini-2.5-flash-image | Media | Price · Standard | Per request | USD 0.032955000000000005 |
| gemini-3-pro-image | Media | Input · Standard | Per 1M tokens | USD 1.6900000000000002 |
| gemini-3.1-flash-image | Media | Input · Standard | Per 1M tokens | USD 0.42250000000000004 |
| gemini-3.1-flash-lite | gemini-stable | Input · Standard | Per 1M tokens | USD 0.0375 |
| gemini-3.1-flash-lite-image | Media | Input · Standard | Per 1M tokens | USD 0.21125000000000002 |
| gemini-3.1-pro-preview | gemini-stable | Input · Context length <= 200000 | Per 1M tokens | USD 0.3 |
| gemini-3.5-flash | gemini-stable | Input · Standard | Per 1M tokens | USD 0.22499999999999998 |
| gemini-3.5-flash-lite | gemini-stable | Input · Standard | Per 1M tokens | USD 0.045 |
| gemini-3.6-flash | gemini-stable | Input · Standard | Per 1M tokens | USD 0.22499999999999998 |
| gemini-3.7-flash | gemini-stable | Input · Standard | Per 1M tokens | USD 0.22499999999999998 |
| gemini-3.8-flash | gemini-stable | Input · Standard | Per 1M tokens | USD 0.22499999999999998 |
| gemini-3.8-flash-high | gemini-stable | Input · Standard | Per 1M tokens | USD 0.22499999999999998 |
| glm-5.2 | glm-award | Input · Standard | Per 1M tokens | USD 0.48999999999999994 |
| glm-5.2 | glm-stable | Input · Standard | Per 1M tokens | USD 0.7 |
| glm-5.3 | glm-award | Input · Standard | Per 1M tokens | USD 0.39999999999999997 |
| glm-5.3 | glm-stable | Input · Standard | Per 1M tokens | USD 0.5714285714285714 |
| glm-5.3-flash | glm-award | Input · Standard | Per 1M tokens | USD 0.039999999999999994 |
| glm-5.3-flash | glm-stable | Input · Standard | Per 1M tokens | USD 0.05714285714285714 |
| gpt-5.4 | openai-award | Input · Standard | Per 1M tokens | USD 0.075 |
| gpt-5.4 | openai-enterprise | Input · Standard | Per 1M tokens | USD 1.25 |
| gpt-5.4 | openai-first-topup | Input · Standard | Per 1M tokens | USD 0.0375 |
| gpt-5.4 | openai-premium | Input · Standard | Per 1M tokens | USD 0.325 |
| gpt-5.4 | openai-stable | Input · Standard | Per 1M tokens | USD 0.2 |
| gpt-5.5 | openai-award | Input · Standard | Per 1M tokens | USD 0.15 |
| gpt-5.5 | openai-enterprise | Input · Standard | Per 1M tokens | USD 2.5 |
| gpt-5.5 | openai-first-topup | Input · Standard | Per 1M tokens | USD 0.075 |
| gpt-5.5 | openai-premium | Input · Standard | Per 1M tokens | USD 0.65 |
| gpt-5.5 | openai-stable | Input · Standard | Per 1M tokens | USD 0.4 |
| gpt-5.6-sol | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.15 |
| gpt-5.6-sol | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 2.5 |
| gpt-5.6-sol | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.075 |
| gpt-5.6-sol | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 0.65 |
| gpt-5.6-sol | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.4 |
| gpt-5.6-terra | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.06 |
| gpt-5.6-terra | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 1 |
| gpt-5.6-terra | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.03 |
| gpt-5.6-terra | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 0.26 |
| gpt-5.6-terra | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.16 |
| gpt-6-astra | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.3 |
| gpt-6-astra | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 5 |
| gpt-6-astra | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.15 |
| gpt-6-astra | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 1.3 |
| gpt-6-astra | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.8 |
| gpt-6-luna | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.0075 |
| gpt-6-luna | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 0.125 |
| gpt-6-luna | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.00375 |
| gpt-6-luna | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 0.0325 |
| gpt-6-luna | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.02 |
| gpt-6-sol | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.06 |
| gpt-6-sol | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 1 |
| gpt-6-sol | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.03 |
| gpt-6-sol | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 0.26 |
| gpt-6-sol | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.16 |
| gpt-6.1-sol | openai-award | Input · Context length <= 272000 | Per 1M tokens | USD 0.06 |
| gpt-6.1-sol | openai-enterprise | Input · Context length <= 272000 | Per 1M tokens | USD 1 |
| gpt-6.1-sol | openai-first-topup | Input · Context length <= 272000 | Per 1M tokens | USD 0.03 |
| gpt-6.1-sol | openai-premium | Input · Context length <= 272000 | Per 1M tokens | USD 0.26 |
| gpt-6.1-sol | openai-stable | Input · Context length <= 272000 | Per 1M tokens | USD 0.16 |
| gpt-image-2 | Media | Input · Standard | Per 1M tokens | USD 3.77 |
| gpt-image-2.5-flare | Media | Input · Standard | Per 1M tokens | USD 5.33 |
| gpt-image-2.5-sunburst | Media | Input · Standard | Per 1M tokens | USD 5.33 |
| grok-4.5 | grok-award | Input · Standard | Per 1M tokens | USD 0.02 |
| grok-4.5 | grok-stable | Input · Standard | Per 1M tokens | USD 0.22 |
| grok-4.6 | grok-award | Input · Standard | Per 1M tokens | USD 0.02 |
| grok-4.6 | grok-stable | Input · Standard | Per 1M tokens | USD 0.22 |
| grok-4.7 | grok-award | Input · Standard | Per 1M tokens | USD 0.02 |
| grok-4.7 | grok-stable | Input · Standard | Per 1M tokens | USD 0.22 |
| happyhorse-1.1-i2v | Media | Output · 1080p | Per second | USD 0.1287 |
| happyhorse-1.1-r2v | Media | Output · 1080p | Per second | USD 0.1287 |
| happyhorse-1.1-t2v | Media | Output · 1080p | Per second | USD 0.1287 |
| jev-1.13 | jev-premium | Input · Standard | Per 1M tokens | USD 0.0483 |
| jev-1.13.0 | jev-premium | Input · Standard | Per 1M tokens | USD 0.0483 |
| kimi-k3 | kimi-award | Input · Standard | Per 1M tokens | USD 1 |
| kimi-k3 | kimi-stable | Input · Standard | Per 1M tokens | USD 1.8571428571428572 |
| kling-2.5-turbo | Media | Output · 1080p | Per second | USD 0.0637 |
| kling-2.6 | Media | Output · 1080p | Per second | USD 0.0637 |
| kling-3.0 | Media | Output · 1080p | Per second | USD 0.10192 |
| kling-3.0-omni | Media | Output · 1080p | Per second | USD 0.10192 |
| kling-3.0-turbo | Media | Output · 1080p | Per second | USD 0.1274 |
| kling-o1 | Media | Output · 1080p | Per second | USD 0.10192 |
| muse-spark-1.3 | spark-premium | Input · Standard | Per 1M tokens | USD 1.4375 |
| qwen3.8-max | qwen-stable | Input · Standard | Per 1M tokens | USD 1.3714285714285714 |
| seedance-2.0 | Media | Output · 1080p | Per 1M tokens | USD 9.509500000000001 |
| seedance-2.0-fast | Media | Output · 480p | Per 1M tokens | USD 3.435714285714286 |
| seedance-2.0-mini | Media | Output · 480p | Per 1M tokens | USD 1.7085714285714286 |
| seedance-2.5 | Media | Output · 1080p | Per 1M tokens | USD 14.4495 |
| seedream-5-0-lite-260128 | Media | Price · Standard | Per image | USD 0.033215 |
| wan2.7-i2v | Media | Output · 1080p | Per second | USD 0.11115000000000001 |
| wan2.7-image | Media | Price · Standard | Per request | USD 0.021192600000000002 |
| wan2.7-image-pro | Media | Price · Standard | Per request | USD 0.0529815 |
| wan2.7-r2v | Media | Output · 1080p | Per second | USD 0.11115000000000001 |
| wan2.7-t2v | Media | Output · 1080p | Per second | USD 0.11115000000000001 |
| wan3.0-video | Media | Output · 1080p | Per second | USD 0.1976 |
| wan3.0-video-prime | Media | Output · 1080p | Per second | USD 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.