Pricing

AI API pricing, billed in EGP

Every model on one OpenAI-compatible API, priced in Egyptian pounds. You pay per token used — no FX conversion on your bill.

244 live models · input from 0.11 to 1707.84 EGP per million tokens

Chat models

191 models

Billed per million tokens, input and output priced separately. Output is usually the larger share of a chat bill, so compare both columns.

Model	Context	Input EGP / 1M	Output EGP / 1M
mistral-nemo-instruct-2407Mistral AI	131K	1.08	1.71
meta-llama-3.1-8b-instruct-turboMeta	131K	1.14	2.28
Meta Llama 3.2 1B InstructMeta	60K	1.54	11.44
gpt-oss-20bOpenAI	131K	1.71	7.97
granite-4.2-3bibm-granite	131K	1.71	6.83
Qwen: Qwen3.7 FlashAlibaba	1M	1.71	7.40
gpt-oss-120bOpenAI	131K	2.11	9.68
gemma-3-12b-itGoogle	131K	2.85	8.54
gemma-3-4b-itGoogle	131K	2.85	5.69
gpt-5-nanoOpenAI	400K	2.85	22.77
Meta Llama 3.2 3B InstructMeta	131K	2.85	18.79
mistral-small-24b-instruct-2501Mistral AI	33K	2.85	4.55
nemotron-3-nano-30b-a3bNVIDIA	262K	2.85	11.39
nim/meta/llama-3.1-8b-instructnim	131K	2.85	4.55
DeepSeek: DeepSeek V4 Flash 0731DeepSeek	1M	3.42	10.25
granite-4.2-8bibm-granite	131K	3.42	14.23
Ling-3.0-flashinclusionai	131K	3.42	10.25
ling-3.0-flash-fininclusionAI	262K	3.42	10.25
ling-3.0-flash-vlinclusionAI	131K	3.42	10.25
glm-4.7-flashzai-org	131K	3.44	22.77
Qwen: Qwen3.5-FlashAlibaba	1M	3.70	14.80
gemma-4-26b-a4b-itGoogle	262K	3.98	19.36
phi-4Microsoft	16K	3.98	7.97
Qwen3 Coder 30B A3b InstructAlibaba	262K	3.98	15.94
mistral-small-3.2-24b-instruct-2506Mistral AI	128K	4.27	11.39
gemma-3-27b-itGoogle	131K	4.55	9.11
nvidia-nemotron-3.5-lightningNVIDIA	262K	4.55	11.39
qwen3-32bAlibaba	41K	4.55	15.94
nvidia-nemotron-3-super-120b-a12bNVIDIA	262K	4.84	22.77
Qwen3-0.6BAlibaba	4K	5.00	10.00
deepseek-v4-flashDeepSeek	1M	5.12	10.25
gemma-4-31b-it-turboGoogle	262K	5.12	19.36
Qwen: Qwen3.8 FlashAlibaba	1M	5.12	16.05
qwen3-235b-a22b-instruct-2507Alibaba	262K	5.12	31.31
qwen3-next-80b-a3b-instructAlibaba	262K	5.12	62.62
Arize AI Qwen 2 1.5B Instructarize-ai	33K	5.69	5.69
gpt-4.1-nanoOpenAI	1M	5.69	22.77
llama-3.3-70b-instruct-turboMeta	131K	5.69	18.22
llama-4-scout-17b-16e-instructMeta	328K	5.69	17.08
nim/meta/llama-3.3-70b-instructnim	131K	5.69	18.22
qwen3.5-9bAlibaba	262K	5.69	8.54
qwen3.6-35b-a3bAlibaba	262K	5.69	54.08
seed-2.0-miniByteDance	256K	5.69	22.77
voxtral-small-24b-2507Mistral AI	33K	5.69	17.08
Qwen3-VL-32B-InstructAlibaba	131K	5.92	23.68
Qwen3 8BAlibaba	131K	6.66	25.90
Qwen3-VL-8B-InstructAlibaba	131K	6.66	25.90
Qwen: Qwen3 Coder NextAlibaba	262K	6.83	45.54
qwen3-14bAlibaba	41K	6.83	13.66
qwen3-30b-a3bAlibaba	41K	6.83	28.46
gemma-4-31b-itGoogle	262K	7.40	21.63
hy3tencent	262K	7.40	30.17
mimo-v2.5XiaomiMiMo	1M	7.97	15.94
qwen3.5-35b-a3bAlibaba	262K	7.97	56.93
Xiaomi: MiMo-V2.6-Flashxiaomi	1M	7.97	15.94
glm-5.3-flashzai-org	1M	8.54	28.46
gpt-4o-miniOpenAI	128K	8.54	34.16
gpt-4o-mini-2024-07-18OpenAI	128K	8.54	34.16
gpt-oss-120b-turboOpenAI	131K	8.54	34.16
Qwen3 Next 80B A3b ThinkingAlibaba	262K	8.54	68.31
qwen3-vl-30b-a3b-instructAlibaba	262K	8.54	34.16
gpt-4o-mini-search-previewOpenAI	128K	8.58	34.32
granite-4.2-30bibm-granite	131K	9.11	37.00
llama-guard-4-12bMeta	164K	10.25	10.25
Qwen: Qwen3.6 FlashAlibaba	1M	10.67	64.04
Qwen: Qwen3 Coder FlashAlibaba	1M	11.10	55.50
deepseek-v4.1-flashDeepSeek	1M	11.39	34.16
gpt-5.4-nanoOpenAI	400K	11.39	71.16
gpt-6-lunaOpenAI	1M	11.39	56.93
nemotron-content-safety-3.5NVIDIA	131K	11.39	11.39
Qwen: Qwen3.8 27BAlibaba	262K	11.39	142.32
qwen3-vl-235b-a22b-instructAlibaba	262K	11.39	50.10
step-3.7-flashstepfun-ai	256K	11.39	65.47
qwen3-235b-a22b-thinking-2507Alibaba	131K	13.09	130.93
Qwen3.8-27B-FP8Alibaba	131K	14.00	105.00
deepseek-v3.1DeepSeek	164K	14.23	54.08
DeepSeek: DeepSeek V3.1DeepSeek	164K	14.23	54.08
gemini-3.1-flash-liteGoogle	1M	14.23	85.39
gpt-5-miniOpenAI	400K	14.23	113.86
gpt-5.1-codex-miniOpenAI	400K	14.23	113.86
seed-1.8ByteDance	256K	14.23	113.86
MiniMax M2MiniMaxAI	205K	14.52	58.07
deepseek-v3.2DeepSeek	164K	14.80	21.63
Qwen: Qwen3.5 Plus 2026-02-15Alibaba	1M	14.80	88.81
qwen3.5-122b-a10bAlibaba	262K	14.80	118.41
qwen3.5-27bAlibaba	262K	14.80	148.01
deepseek-v3.1-terminusDeepSeek	131K	15.37	56.93
gemma-4-31b-it-ultraGoogle	131K	15.37	43.27
minimax-m3MiniMaxAI	524K	15.94	62.62
DeepSeek: DeepSeek V3 0324DeepSeek	164K	16.51	64.90
gemini-2.5-flashGoogle	1M	17.08	142.32
minimax-m2.7MiniMaxAI	205K	17.08	68.31
Qwen: Qwen3.5 Plus 2026-04-20Alibaba	1M	17.08	102.47
deepseek-v3DeepSeek	164K	18.22	50.67
qwen3.6-27bAlibaba	262K	18.22	182.17
Qwen3.7 PlusAlibaba	1M	18.22	72.87
Muse Glimmer 30Bmeta-models	131K	19.92	85.39
minimax-m2.7-turboMiniMaxAI	197K	21.63	96.78
glm-4.7zai-org	203K	22.77	99.62
gpt-4.1-miniOpenAI	1M	22.77	91.08
gpt-5.6-lunaOpenAI	1M	22.77	136.63
meta-llama-3.1-70b-instruct-turboMeta	131K	22.77	22.77
nim/meta/llama-3.1-70b-instructnim	131K	22.77	22.77
Xiaomi: MiMo-V2.6-Proxiaomi	1M	24.48	49.53
mimo-v2.5-proXiaomiMiMo	1M	24.76	49.53
DeepSeek: DeepSeek V4 Flash Vision ExpDeepSeek	1M	25.05	75.15
kimi-k2.5moonshotai	262K	25.62	128.09
qwen3.5-397b-a17bAlibaba	262K	25.62	170.78
Thinking Machines: Inkling Smallthinkingmachines	524K	25.62	68.31
deepseek-r1-0528DeepSeek	164K	28.46	122.40
glm-4.6zai-org	203K	28.46	113.86
gpt-3.5-turboOpenAI	16K	28.46	85.39
nvidia-nemotron-3-ultra-550b-a55bNVIDIA	262K	28.46	125.24
Qwen3.6 PlusAlibaba	1M	28.46	170.78
seed-2.0-codeByteDance	256K	28.46	170.78
seed-2.0-proByteDance	256K	28.46	170.78
MoonshotAI: Kimi K2 0711moonshotai	131K	32.45	130.93
GLM 4.5Vzai-org	66K	34.16	102.47
glm-5zai-org	198K	34.16	109.30
MoonshotAI: Kimi K2 0905moonshotai	262K	34.16	142.32
NVIDIA Nemotron 3 Ultra 550B A55B NVFP4NVIDIA	203K	34.16	136.63
Gemma-2 Instruct (27B)Google	8K	37.00	37.00
kimi-k2.7-codemoonshotai	262K	37.36	187.86
DeepSeek: R1DeepSeek	64K	39.85	142.32
hermes-3-llama-3.1-70bNousResearch	131K	39.85	39.85
glm-5.2zai-org	1M	42.70	136.63
Google: Gemini 3.6 FlashGoogle	1M	42.70	213.48
Google: Gemini 3.7 FlashGoogle	1M	42.70	213.48
Google: Gemini 3.8 FlashGoogle	1M	42.70	213.48
gpt-5.4-miniOpenAI	400K	42.70	256.18
kimi-k2.6moonshotai	262K	42.70	199.25
DeepSeek R1 Distill Llama 70BDeepSeek	8K	45.54	45.54
Qwen2.5-VL (72B) InstructAlibaba	128K	45.54	56.93
Tencent: Hy4 previewtencent	1M	47.48	142.38
Z.ai: GLM 5.3z-ai	1M	51.24	227.71
Inkling FP4thinkingmachines	524K	54.08	230.56
claude-haiku-4.5Anthropic	200K	56.93	284.64
Qwen: Qwen3.6 Max PreviewAlibaba	262K	58.47	350.79
o3-miniOpenAI	200K	62.62	250.48
o4-miniOpenAI	200K	62.62	250.48
qwen3-maxAlibaba	256K	68.31	341.57
qwen3-max-thinkingAlibaba	256K	68.31	341.57
gemini-2.5-proGoogle	1M	71.16	569.28
gpt-5OpenAI	400K	71.16	569.28
gpt-5.1OpenAI	400K	71.16	569.28
gpt-5.1-codexOpenAI	400K	71.16	569.28
gpt-5.1-codex-maxOpenAI	400K	71.16	569.28
deepseek-v4-proDeepSeek	1M	74.01	148.01
DeepSeek: DeepSeek V4 Pro 0813DeepSeek	1M	74.01	148.01
glm-5.1zai-org	203K	79.70	250.48
gemini-3.5-flashGoogle	1M	85.39	512.35
gpt-3.5-turbo-instructOpenAI	4K	85.39	113.86
Qwen3.7 MaxAlibaba	1M	85.39	256.18
Qwen: Qwen3.8 MaxAlibaba	256K	93.93	281.85
gpt-5.2OpenAI	400K	99.62	796.99
gpt-5.2-codexOpenAI	400K	99.62	796.99
gpt-5.3-codexOpenAI	400K	99.62	796.99
claude-sonnet-5Anthropic	1M	113.86	569.28
gemini-3.1-proGoogle	1M	113.86	683.14
gpt-4.1OpenAI	1M	113.86	455.42
gpt-5.6-solOpenAI	1M	113.86	569.28
gpt-5.6-terraOpenAI	1M	113.86	683.14
gpt-6-solOpenAI	1M	113.86	569.28
o3OpenAI	200K	113.86	455.42
qwen3.8-2.4t-a95bAlibaba	262K	113.86	341.57
gpt-4oOpenAI	128K	142.32	569.28
gpt-4o-2024-08-06OpenAI	128K	142.32	569.28
gpt-4o-2024-11-20OpenAI	128K	142.32	569.28
gpt-5.4OpenAI	1M	142.32	853.92
gpt-4o-search-previewOpenAI	128K	143.00	572.00
MoonshotAI: Kimi K3moonshotai	1M	162.25	811.23
Claude Sonnet 4.5Anthropic	1M	170.78	853.92
claude-sonnet-4.6Anthropic	1M	170.78	853.92
gpt-3.5-turbo-16kOpenAI	16K	170.78	227.71
Claude Opus 5.5Anthropic	1M	227.71	1138.56
Claude Opus 4.5Anthropic	200K	284.64	1423.20
Claude Opus 4.6Anthropic	1M	284.64	1423.20
Claude Opus 5Anthropic	1M	284.64	1423.20
claude-opus-4.7Anthropic	1M	284.64	1423.20
claude-opus-4.8Anthropic	1M	284.64	1423.20
gpt-4o-2024-05-13OpenAI	128K	284.64	853.92
gpt-5.5OpenAI	1M	284.64	1707.84
gpt-image-2Provider	400K	455.42	455.42
Claude Fable 5.1Anthropic	1M	569.28	2846.40
claude-fable-5Anthropic	1M	569.28	2846.40
gpt-6-astraOpenAI	1M	569.28	2846.40
o1OpenAI	200K	853.92	3415.68
o3-proOpenAI	200K	1138.56	4554.25
gpt-5.2-proOpenAI	400K	1195.49	9563.92
gpt-4OpenAI	8K	1707.84	3415.68
gpt-4-turboOpenAI	8K	1707.84	3415.68

Embedding models

28 models

Billed on input tokens only. Embeddings return vectors, not generated text, so there is no output charge.

Model	Context	Input EGP / 1M
embeddinggemma-300mGoogle	2K	0.11
all-minilm-l12-v2SBERT	512	0.28
all-minilm-l6-v2SBERT	512	0.28
all-mpnet-base-v2SBERT	512	0.28
bge-base-en-v1.5BAAI	512	0.28
clip-vit-b-32SBERT	77	0.28
clip-vit-b-32-multilingual-v1SBERT	512	0.28
e5-base-v2intfloat	512	0.28
gte-basethenlper	512	0.28
multi-qa-mpnet-base-dot-v1SBERT	512	0.28
paraphrase-minilm-l6-v2SBERT	512	0.28
text2vec-base-chineseshibing624	512	0.28
bge-en-iclBAAI	8K	0.57
bge-large-en-v1.5BAAI	512	0.57
bge-m3BAAI	8K	0.57
bge-m3-multiBAAI	512	0.57
bge-m3-multi-8kBAAI	8K	0.57
e5-large-v2intfloat	512	0.57
gte-largethenlper	512	0.57
llama-nemotron-embed-vl-1b-v2NVIDIA	10K	0.57
multilingual-e5-largeintfloat	512	0.57
multilingual-e5-large-instructintfloat	512	0.57
qwen3-embedding-0.6bAlibaba	33K	0.57
qwen3-embedding-8bAlibaba	33K	0.57
qwen3-embedding-4bAlibaba	33K	1.14
text-embedding-3-smallOpenAI	—	1.14
text-embedding-ada-002OpenAI	—	5.69
text-embedding-3-largeOpenAI	—	7.40

Image generation models

25 models

Billed per generated image. Where a figure is marked ≈, the exact charge depends on the request and is reported on every response.

Model	Price
sdxl-turbostabilityai	0.0114 EGP per 1024p image
flux-1-schnellblack-forest-labs	0.0285 EGP per 1024p image
p-imagePrunaAI	0.2846 EGP per image
flux-1-devblack-forest-labs	0.5124 EGP per 1024p image
ming-image-0.1-designinclusionAI	0.5693 EGP per 1024p image
ming-image-0.1-design-layerinclusionAI	0.5693 EGP per 1024p image
flux-2-klein-4bblack-forest-labs	0.797 EGP per 1024p image
flux-2-klein-9bblack-forest-labs	0.8539 EGP per 1024p image
flux-2-problack-forest-labs	≈ 0.8539 EGP per image
flux-2-devblack-forest-labs	1.02 EGP per 1024p image
wan2.6-t2iWan-AI	1.71 EGP per image
nano-banana-2-liteGoogle	1.91 EGP per image
bria-3.2Bria	2.28 EGP per image
bria-3.2-vectorBria	2.28 EGP per image
fiboBria	2.28 EGP per image
fibo-1.5Bria	2.28 EGP per image
flux-1.1-problack-forest-labs	2.28 EGP per image
seedream-4ByteDance	2.28 EGP per image
seedream-4.5ByteDance	2.28 EGP per image
nano-banana-2Google	3.83 EGP per image
flux-2-maxblack-forest-labs	≈ 3.98 EGP per image
qwen-image-maxAlibaba	4.27 EGP per image
seedream-5.0-proByteDance	5.64 EGP per image
gemini-3-pro-imageGoogle	7.65 EGP per image
nano-banana-proGoogle	7.65 EGP per image

How billing works

Rates are per million tokens, and you are charged only for the tokens a request actually uses. Each model page shows its context window, modalities and full rate details. For request formats and limits, see the documentation; to filter and compare models, use the model library.