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.

402 live models · input from 0.11 to 8595.23 EGP per million tokens

Chat models

347 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
DeepSeek: DeepSeek V4 Flash Latest~deepseek	1M	0.45	7.49
IBM: Granite 4.0 Microibm-granite	131K	0.97	6.42
DeepSeek: DeepSeek Flash Latest~deepseek	1M	1.07	22.69
mistral-nemo-instruct-2407Mistral AI	131K	1.09	1.72
Mistral: Mistral NemoMistral AI	131K	1.09	1.72
meta-llama-3.1-8b-instruct-turboMeta	131K	1.15	2.29
Z.ai: GLM Flash Latest~z-ai	1M	1.15	14.18
Nex AGI: Nex-N2.5-Mininex-agi	262K	1.43	5.73
Meta: Llama 3.2 1B InstructMeta	60K	1.55	11.52
gpt-oss-20bOpenAI	131K	1.72	8.02
granite-4.2-3bibm-granite	131K	1.72	6.88
Inference.net: Schematron V2 Turboinference-net	128K	1.72	8.60
Qwen: Qwen3.7 FlashAlibaba	1M	1.72	7.45
Amazon: Nova Micro 1.0amazon	128K	2.01	8.02
gpt-oss-120bOpenAI	131K	2.12	9.74
Cohere: Command R7B (12-2024)cohere	128K	2.15	8.60
Inception: Mercury 2.5G42 / Inception	260K	2.29	8.60
Tencent: Hy-MT2-1.8Btencent	8K	2.52	10.14
Qwen: Qwen3 30B A3B Instruct 2507Alibaba	128K	2.76	11.06
gemma-3-12b-itGoogle	131K	2.87	8.60
Inference.net: Schematron V2 Smallinference-net	128K	2.87	13.18
Meta: Llama 3.1 8B InstructMeta	131K	2.87	4.58
Meta: Llama 3.2 3B InstructMeta	131K	2.87	18.91
mistral-small-24b-instruct-2501Mistral AI	33K	2.87	4.58
nemotron-3-nano-30b-a3bNVIDIA	262K	2.87	11.46
OpenAI: GPT-5 NanoOpenAI	400K	2.87	22.92
Upstage: Solar Mini 4upstage	524K	2.87	11.46
NVIDIA: Nemotron 3.5 LightningNVIDIA	262K	3.41	9.74
Amazon: Nova Lite 1.0amazon	300K	3.44	13.75
DeepSeek: DeepSeek V4 Flash 0731DeepSeek	1M	3.44	10.31
IBM: Granite 4.2 8Bibm-granite	131K	3.44	14.33
inclusionAI: Ling 3.0 Flashinclusionai	131K	3.44	10.31
inclusionAI: Ling 3.0 Flash Fininclusionai	262K	3.44	10.31
inclusionAI: Ling 3.0 Flash VLinclusionai	131K	3.44	10.31
nvidia-nemotron-3.5-lightningNVIDIA	262K	3.44	9.17
Poolside: Laguna XS 2.1poolside	262K	3.44	6.88
Z.ai: GLM 4.7 Flashz-ai	131K	3.47	22.92
Qwen: Qwen3.5-FlashAlibaba	1M	3.72	14.90
Google: Gemma 4 26B A4B Google	262K	4.01	19.48
phi-4Microsoft	16K	4.01	8.02
Qwen: Qwen3 Coder 30B A3B InstructAlibaba	262K	4.01	16.04
Tencent: Hy-MT2-30B-A3Btencent	8K	4.24	16.90
Tencent: Hy-MT2-7Btencent	8K	4.24	16.90
ByteDance Seed: Seed 1.6 Flashbytedance-seed	262K	4.30	17.19
mistral-small-3.2-24b-instruct-2506Mistral AI	128K	4.30	11.46
Nex AGI: Nex-N2.5-Pronex-agi	262K	4.30	14.33
OpenAI: gpt-oss-safeguard-20bOpenAI	131K	4.30	17.19
PrismML: Ternary Bonsai 2 27Bprism-ml	262K	4.30	28.65
gemma-3-27b-itGoogle	131K	4.58	9.17
NVIDIA: Nemotron 3 SuperNVIDIA	262K	4.58	25.79
qwen3-32bAlibaba	41K	4.58	16.04
nvidia-nemotron-3-super-120b-a12bNVIDIA	262K	4.87	22.92
Qwen: Qwen3 235B A22B Instruct 2507Alibaba	262K	5.01	20.06
DeepSeek: DeepSeek V4 Flash 0423DeepSeek	1M	5.16	10.31
gemma-4-31b-it-turboGoogle	262K	5.16	19.48
Poolside: Laguna S 2.1poolside	1M	5.16	10.31
qwen3-235b-a22b-instruct-2507Alibaba	262K	5.16	31.52
qwen3-next-80b-a3b-instructAlibaba	262K	5.16	63.03
Upstage: Solar Pro 4upstage	524K	5.16	20.63
Mistral: Mistral Small 3.2 24BMistral AI	256K	5.37	14.33
ByteDance Seed: Seed-2.0-Minibytedance-seed	256K	5.73	22.92
ByteDance: UI-TARS 7B bytedance	128K	5.73	11.46
Google: Gemini 2.5 Flash LiteGoogle	1M	5.73	22.92
llama-3.3-70b-instruct-turboMeta	66K	5.73	18.34
llama-4-scout-17b-16e-instructMeta	328K	5.73	17.19
Meta: Llama 3.3 70B InstructMeta	66K	5.73	18.34
Meta: Llama 4 ScoutMeta	328K	5.73	17.19
Mistral: Ministral 3 3B 2512Mistral AI	131K	5.73	5.73
OpenAI: GPT Luna Latest~openai	1M	5.73	28.65
OpenAI: GPT-4.1 NanoOpenAI	1M	5.73	22.92
OpenAI: GPT-6 LunaOpenAI	1M	5.73	28.65
OpenAI: GPT-6 Luna ProOpenAI	1M	5.73	28.65
Qwen: Qwen3.5-9BAlibaba	262K	5.73	8.60
Qwen: Qwen3.6 35B A3BAlibaba	262K	5.73	54.44
Reka Edgerekaai	16K	5.73	5.73
Reka Flash 3rekaai	66K	5.73	11.46
StepFun: Step 3.5 Flashstepfun	262K	5.73	17.19
voxtral-small-24b-2507Mistral AI	33K	5.73	17.19
Qwen: Qwen3 VL 32B InstructAlibaba	131K	5.96	23.84
Qwen: Qwen3.8 FlashAlibaba	1M	6.48	21.89
Qwen: Qwen3 8BAlibaba	131K	6.70	26.07
Qwen: Qwen3 VL 8B InstructAlibaba	131K	6.70	26.07
Qwen: Qwen3 Coder NextAlibaba	262K	6.88	45.84
qwen3-14bAlibaba	41K	6.88	13.75
qwen3-30b-a3bAlibaba	41K	6.88	28.65
DeepSeek: DeepSeek Pro Latest~deepseek	1M	7.05	200.56
Google: Gemma 4 31BGoogle	262K	7.45	21.77
Tencent: Hy3tencent	262K	7.45	30.37
Z.ai: GLM 4.5 Airz-ai	131K	7.45	48.71
Qwen: Qwen3.5-35B-A3BAlibaba	262K	8.02	57.30
Tencent: Hunyuan A13B Instructtencent	131K	8.02	32.66
Xiaomi: MiMo-V2.5xiaomi	1M	8.02	16.04
Xiaomi: MiMo-V2.6-Flashxiaomi	1M	8.02	16.04
Cohere: Command R (08-2024)cohere	128K	8.60	34.38
gpt-oss-120b-turboOpenAI	131K	8.60	34.38
Mistral: Ministral 3 8B 2512Mistral AI	262K	8.60	8.60
OpenAI: GPT-4o-miniOpenAI	128K	8.60	34.38
OpenAI: GPT-4o-mini (2024-07-18)OpenAI	128K	8.60	34.38
Perceptron: Perceptron Mk1perceptron	33K	8.60	85.95
Perceptron: Perceptron Mk1.5perceptron	37K	8.60	85.95
Qwen: Qwen3 Next 80B A3B ThinkingAlibaba	262K	8.60	68.76
Qwen: Qwen3 VL 30B A3B InstructAlibaba	262K	8.60	34.38
Qwen: Qwen3.8 Omni FlashAlibaba	1M	8.60	26.93
Upstage: Solar Pro 3upstage	131K	8.60	34.38
Z.ai: GLM 5.3 Flashz-ai	1M	8.60	28.65
Z.ai: GLM Latest~z-ai	1M	8.82	27.73
granite-4.2-30bibm-granite	131K	9.17	37.25
llama-guard-4-12bMeta	164K	10.31	10.31
Qwen: Qwen3 VL 8B ThinkingAlibaba	131K	10.31	120.33
Tencent: Hy3 previewtencent	262K	10.31	34.38
Meta: Llama 4 MaverickMeta	128K	10.74	37.39
Qwen: Qwen3.6 FlashAlibaba	1M	10.74	64.46
Qwen: Qwen3 Coder FlashAlibaba	1M	11.17	55.87
DeepSeek: DeepSeek V4.1 FlashDeepSeek	1M	11.46	34.38
gpt-oss-120b-ultraOpenAI	131K	11.46	54.44
MiniMax: MiniMax-01minimax	1M	11.46	63.03
Mistral: Ministral 3 14B 2512Mistral AI	262K	11.46	11.46
nemotron-content-safety-3.5NVIDIA	131K	11.46	11.46
NVIDIA: Nemotron 3.5 Content SafetyNVIDIA	131K	11.46	11.46
OpenAI: GPT-5.4 NanoOpenAI	400K	11.46	71.63
OpenAI: GPT-5.6 LunaOpenAI	1M	11.46	68.76
OpenAI: GPT-5.6 Luna ProOpenAI	1M	11.46	68.76
Qwen: Qwen3 30B A3B Thinking 2507Alibaba	82K	11.46	137.52
Qwen: Qwen3 VL 30B A3B ThinkingAlibaba	131K	11.46	137.52
Qwen: Qwen3.8 27BAlibaba	262K	11.46	143.25
qwen3-vl-235b-a22b-instructAlibaba	262K	11.46	50.43
StepFun: Step 3.7 Flashstepfun	256K	11.46	65.90
MiniMax: MiniMax M2.7minimax	197K	12.03	48.13
Qwen: Qwen3 235B A22B Thinking 2507Alibaba	131K	13.18	131.79
Arcee AI: Trinity Large Thinkingarcee-ai	262K	14.33	45.84
ByteDance Seed: Seed 1.6bytedance-seed	262K	14.33	114.60
ByteDance Seed: Seed-2.0-Litebytedance-seed	262K	14.33	114.60
deepseek-v3.1DeepSeek	164K	14.33	54.44
DeepSeek: DeepSeek V3.1DeepSeek	164K	14.33	54.44
Google: Gemini 3.1 Flash LiteGoogle	1M	14.33	85.95
Google: Gemini 3.1 Flash Lite PreviewGoogle	1M	14.33	85.95
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google	66K	14.33	85.95
Inception: Mercury 2G42 / Inception	128K	14.33	42.98
OpenAI: GPT-5 MiniOpenAI	400K	14.33	114.60
OpenAI: GPT-5.1-Codex-MiniOpenAI	400K	14.33	114.60
seed-1.8ByteDance	256K	14.33	114.60
DeepSeek: DeepSeek V3DeepSeek	128K	14.75	58.95
DeepSeek: DeepSeek V3.2DeepSeek	164K	14.90	21.77
Qwen: Qwen Plus 0728Alibaba	1M	14.90	44.70
Qwen: Qwen3.5 Plus 2026-02-15Alibaba	1M	14.90	89.39
Qwen: Qwen3.5-122B-A10BAlibaba	262K	14.90	119.19
Qwen: Qwen3.5-27BAlibaba	262K	14.90	148.98
DeepSeek: DeepSeek V3.2 ExpDeepSeek	164K	15.47	23.49
MiniMax: MiniMax M2.5minimax	200K	15.47	61.89
MiniMax: MiniMax M3minimax	524K	16.04	63.03
MoonshotAI: Kimi Latest~moonshotai	1M	16.04	573.02
DeepSeek: DeepSeek V3 0324DeepSeek	164K	16.62	65.32
Amazon: Nova 2 Liteamazon	1M	17.19	143.25
Cohere: Command A+cohere	192K	17.19	85.95
DeepSeek: DeepSeek V3.1 TerminusDeepSeek	131K	17.19	57.30
gemini-2.5-flashGoogle	1M	17.19	143.25
Google: Gemini 3.5 Flash LiteGoogle	1M	17.19	143.25
Google: Nano Banana (Gemini 2.5 Flash Image)Google	33K	17.19	143.25
Meituan: LongCat 2.0meituan	1M	17.19	68.76
Meta: Muse Glimmer 30BMeta	131K	17.19	68.76
MiniMax: MiniMax M2minimax	197K	17.19	68.76
MiniMax: MiniMax M2-herminimax	66K	17.19	68.76
MiniMax: MiniMax M2.1minimax	205K	17.19	68.76
Mistral: Codestral 2508Mistral AI	256K	17.19	51.57
Qwen: Qwen3 Coder 480B A35BAlibaba	262K	17.19	57.30
Qwen: Qwen3.5 Plus 2026-04-20Alibaba	1M	17.19	103.14
qwen3-coder-480b-a35b-instruct-turboAlibaba	262K	17.19	57.30
Z.ai: GLM 4.6Vz-ai	131K	17.19	51.57
deepseek-v3DeepSeek	164K	18.34	51.00
Qwen: Qwen3.6 27BAlibaba	262K	18.34	183.36
Qwen: Qwen3.7 PlusAlibaba	1M	18.34	73.35
Qwen: Qwen3.6 PlusAlibaba	1M	18.62	111.74
Mistral: Mistral Small 3.1 24BMistral AI	128K	20.11	31.80
Qwen2.5 72B InstructAlibaba	33K	20.63	22.92
qwen2.5-72b-instructAlibaba	33K	20.63	22.92
Z.ai: GLM 5.3 FlashXz-ai	1M	21.20	71.63
Mancer: Weaver (alpha)mancer	8K	22.92	42.98
meta-llama-3.1-70b-instruct-turboMeta	131K	22.92	22.92
Meta: Llama 3.1 70B InstructMeta	131K	22.92	22.92
Mistral: Devstral 2 2512Mistral AI	262K	22.92	114.60
Mistral: Mistral Medium 3Mistral AI	131K	22.92	114.60
Mistral: Mistral Medium 3.1Mistral AI	131K	22.92	114.60
OpenAI: GPT-4.1 MiniOpenAI	1M	22.92	91.68
Z.ai: GLM 4.7z-ai	203K	22.92	100.28
Baidu: ERNIE 4.5 VL 424B A47B baidu	123K	24.07	71.63
Xiaomi: MiMo-V2.6-Proxiaomi	1M	24.64	49.85
Xiaomi: MiMo-V2.5-Proxiaomi	1M	24.93	49.85
DeepSeek: DeepSeek V4 Flash Vision ExpDeepSeek	1M	25.21	75.64
MoonshotAI: Kimi K2.5moonshotai	262K	25.79	128.93
Qwen: Qwen3.5 397B A17BAlibaba	262K	25.79	171.90
Thinking Machines: Inkling Smallthinkingmachines	524K	25.79	68.76
Qwen: Qwen3 235B A22BAlibaba	131K	26.07	104.29
ByteDance Seed: Seed 2.1 Turbobytedance-seed	262K	28.65	143.25
ByteDance Seed: Seed-2.0-Codebytedance-seed	256K	28.65	171.90
deepseek-r1-0528DeepSeek	164K	28.65	123.20
glm-4.6zai-org	203K	28.65	114.60
Google: Gemini 3 Flash PreviewGoogle	1M	28.65	171.90
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)Google	66K	28.65	171.90
Google: Nano Banana 2 (Gemini 3.1 Flash Image)Google	131K	28.65	171.90
nvidia-nemotron-3-ultra-550b-a55bNVIDIA	262K	28.65	126.06
OpenAI: GPT-3.5 TurboOpenAI	16K	28.65	85.95
seed-2.0-proByteDance	256K	28.65	171.90
MiniMax: MiniMax M1minimax	1M	31.52	126.06
MoonshotAI: Kimi K2 0711moonshotai	131K	32.66	131.79
MoonshotAI: Kimi K2 0905moonshotai	262K	34.38	143.25
MoonshotAI: Kimi K2 Thinkingmoonshotai	262K	34.38	143.25
NVIDIA: Nemotron 3 UltraNVIDIA	203K	34.38	137.52
Writer: Palmyra X5writer	1M	34.38	343.81
Z.ai: GLM 4.5z-ai	131K	34.38	126.06
Z.ai: GLM 4.5Vz-ai	66K	34.38	103.14
Z.ai: GLM 5z-ai	198K	34.38	110.02
WizardLM-2 8x22BMicrosoft	66K	35.53	35.53
Google: Gemma 2 27BGoogle	8K	37.25	37.25
Qwen: Qwen3 Coder PlusAlibaba	1M	37.25	186.23
Qwen2.5 Coder 32B InstructAlibaba	33K	37.82	57.30
MoonshotAI: Kimi K2.7 Codemoonshotai	262K	38.46	191.96
AionLabs: Aion 3.5 Miniaion-labs	262K	40.11	80.22
AionLabs: Aion-3.0-Miniaion-labs	131K	40.11	80.22
DeepSeek: R1DeepSeek	64K	40.11	143.25
hermes-3-llama-3.1-70bNousResearch	131K	40.11	40.11
Google: Gemini 3.6 FlashGoogle	1M	42.98	214.88
Google: Gemini 3.7 FlashGoogle	1M	42.98	214.88
Google: Gemini 3.8 FlashGoogle	1M	42.98	214.88
Google: Gemini Flash Latest~google	1M	42.98	214.88
MoonshotAI: Kimi K2.6moonshotai	262K	42.98	200.56
OpenAI: GPT Mini Latest~openai	400K	42.98	257.86
OpenAI: GPT-5.4 MiniOpenAI	400K	42.98	257.86
Z.ai: GLM 5.2z-ai	1M	42.98	137.52
AionLabs: Aion-2.0aion-labs	131K	45.84	91.68
AionLabs: Aion-RP 1.0 (8B)aion-labs	33K	45.84	91.68
Amazon: Nova Pro 1.0amazon	300K	45.84	183.36
Morph: Morph V3 Fastmorph	82K	45.84	68.76
Qwen: Qwen2.5 VL 72B InstructAlibaba	128K	45.84	57.30
Tencent: Hy4 previewtencent	1M	47.79	143.31
Morph: Morph V3 Largemorph	262K	51.57	108.87
Z.ai: GLM 5.3z-ai	1M	51.57	229.21
Thinking Machines: Inklingthinkingmachines	524K	54.44	232.07
Z.ai: GLM 5.1z-ai	203K	55.27	173.72
Anthropic: Claude Haiku Latest~anthropic	200K	57.30	286.51
claude-haiku-4.5Anthropic	200K	57.30	286.51
hermes-3-llama-3.1-405bNousResearch	131K	57.30	57.30
Nous: Hermes 4 405Bnousresearch	131K	57.30	171.90
OpenAI: GPT-3.5 Turbo (older v0613)OpenAI	4K	57.30	114.60
Perplexity: Sonarperplexity	127K	57.30	57.30
Relace: Relace Searchrelace	256K	57.30	171.90
SpaceXAI: Grok Build 0.1x-ai	256K	57.30	114.60
Qwen: Qwen3.6 Max PreviewAlibaba	262K	58.85	353.09
OpenAI: o3 MiniOpenAI	200K	63.03	252.13
OpenAI: o3 Mini HighOpenAI	200K	63.03	252.13
OpenAI: o4 MiniOpenAI	200K	63.03	252.13
OpenAI: o4 Mini HighOpenAI	200K	63.03	252.13
Qwen: Qwen3 Max ThinkingAlibaba	256K	68.76	343.81
qwen3-maxAlibaba	256K	68.76	343.81
Z.ai: GLM 5 Turboz-ai	203K	68.76	229.21
Z.ai: GLM 5V Turboz-ai	203K	68.76	229.21
gemini-2.5-proGoogle	1M	71.63	573.02
Google: Gemini 2.5 Pro Preview 06-05Google	1M	71.63	573.02
OpenAI: GPT-5OpenAI	400K	71.63	573.02
OpenAI: GPT-5.1OpenAI	400K	71.63	573.02
OpenAI: GPT-5.1-CodexOpenAI	400K	71.63	573.02
OpenAI: GPT-5.1-Codex-MaxOpenAI	400K	71.63	573.02
SpaceXAI: Grok 4.20x-ai	2M	71.63	143.25
SpaceXAI: Grok 4.3x-ai	1M	71.63	143.25
DeepSeek: DeepSeek V4 Pro 0423DeepSeek	1M	74.49	148.98
DeepSeek: DeepSeek V4 Pro 0813DeepSeek	1M	74.49	148.98
Google: Gemini 3.5 FlashGoogle	1M	85.95	515.71
Mistral: Mistral Medium 3.5Mistral AI	262K	85.95	429.76
qwen3.8-maxAlibaba	256K	94.55	283.70
Qwen2.5-7B-InstructAlibaba	4K	100.00	500.00
OpenAI: GPT-5.2OpenAI	400K	100.28	802.22
OpenAI: GPT-5.2-CodexOpenAI	400K	100.28	802.22
OpenAI: GPT-5.3-CodexOpenAI	400K	100.28	802.22
Anthropic: Claude Sonnet 5.5Anthropic	1M	114.60	573.02
Anthropic: Claude Sonnet Latest~anthropic	1M	114.60	573.02
gemini-3.1-proGoogle	1M	114.60	687.62
Google: Gemini 3.1 Pro PreviewGoogle	1M	114.60	687.62
Google: Gemini 3.1 Pro Preview Custom ToolsGoogle	1M	114.60	687.62
Google: Gemini Pro Latest~google	1M	114.60	687.62
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)Google	66K	114.60	687.62
Mistral LargeMistral AI	128K	114.60	343.81
Mistral Large 2407Mistral AI	131K	114.60	343.81
OpenAI: GPT Sol Latest~openai	1M	114.60	573.02
OpenAI: GPT Terra Latest~openai	1M	114.60	687.62
OpenAI: GPT-4.1OpenAI	1M	114.60	458.41
OpenAI: GPT-5.6 SolOpenAI	1M	114.60	573.02
OpenAI: GPT-5.6 TerraOpenAI	1M	114.60	687.62
OpenAI: GPT-6 SolOpenAI	1M	114.60	573.02
OpenAI: GPT-6 Sol ProOpenAI	1M	114.60	573.02
OpenAI: GPT-6.1 SolOpenAI	1M	114.60	573.02
OpenAI: GPT-6.1 Sol ProOpenAI	1M	114.60	573.02
OpenAI: o3OpenAI	200K	114.60	458.41
Perplexity: Sonar Reasoning Properplexity	128K	114.60	458.41
Qwen: Qwen3.8 2.4T A95BAlibaba	262K	114.60	343.81
Qwen: Qwen3.8 Max (0902)Alibaba	1M	114.60	343.81
SpaceXAI: Grok 4.5x-ai	500K	114.60	343.81
SpaceXAI: Grok 4.7x-ai	500K	114.60	343.81
xAI: Grok Latest~x-ai	500K	114.60	343.81
Cohere: Command Acohere	256K	143.25	573.02
Cohere: Command R+ (08-2024)cohere	128K	143.25	573.02
OpenAI: GPT-4oOpenAI	128K	143.25	573.02
OpenAI: GPT-4o (2024-08-06)OpenAI	128K	143.25	573.02
OpenAI: GPT-4o (2024-11-20)OpenAI	128K	143.25	573.02
OpenAI: GPT-5 Image MiniOpenAI	400K	143.25	114.60
OpenAI: GPT-5.4OpenAI	1M	143.25	859.52
Paretounbiased	262K	143.25	429.76
Qwen: Qwen3.7 MaxAlibaba	256K	143.25	429.76
Z.ai: GLM 5.3 Primez-ai	1M	160.44	504.25
MoonshotAI: Kimi K3moonshotai	1M	163.31	816.55
AionLabs: Aion 3.5aion-labs	262K	171.90	343.81
AionLabs: Aion-3.0aion-labs	131K	171.90	343.81
Anthropic: Claude Sonnet 4Anthropic	200K	171.90	859.52
Anthropic: Claude Sonnet 4.5Anthropic	1M	171.90	859.52
Anthropic: Claude Sonnet 4.6Anthropic	1M	171.90	859.52
Anthropic: Claude Sonnet 5Anthropic	1M	171.90	859.52
OpenAI: GPT-3.5 Turbo 16kOpenAI	16K	171.90	229.21
Perplexity: Sonar Properplexity	200K	171.90	859.52
Perplexity: Sonar Pro Searchperplexity	200K	171.90	859.52
Anthropic: Claude Opus 5.5Anthropic	1M	229.21	1146.03
Anthropic: Claude Opus Latest~anthropic	1M	229.21	1146.03
OpenAI: GPT-5.6 Sol ProOpenAI	1M	229.21	1146.03
Qwen: Qwen3.8 Max PrimeAlibaba	1M	229.21	687.62
Xiaomi: MiMo-V2.6-Pro-UltraSpeedxiaomi	1M	249.26	498.52
Anthropic: Claude Opus 4.5Anthropic	200K	286.51	1432.54
Anthropic: Claude Opus 4.6Anthropic	1M	286.51	1432.54
Anthropic: Claude Opus 4.7Anthropic	1M	286.51	1432.54
Anthropic: Claude Opus 4.8Anthropic	1M	286.51	1432.54
Anthropic: Claude Opus 5Anthropic	1M	286.51	1432.54
OpenAI: GPT Chat LatestOpenAI	400K	286.51	1719.05
OpenAI: GPT-4o (2024-05-13)OpenAI	128K	286.51	859.52
OpenAI: GPT-5.5OpenAI	1M	286.51	1719.05
OpenAI: GPT-5.4 Image 2OpenAI	272K	458.41	859.52
Anthropic: Claude Fable 5Anthropic	1M	573.02	2865.08
Anthropic: Claude Fable 5.1Anthropic	1M	573.02	2865.08
Anthropic: Claude Fable Latest~anthropic	1M	573.02	2865.08
OpenAI: GPT Astra Latest~openai	1M	573.02	2865.08
OpenAI: GPT-4 TurboOpenAI	128K	573.02	1719.05
OpenAI: GPT-5 ImageOpenAI	400K	573.02	573.02
OpenAI: GPT-6 AstraOpenAI	1M	573.02	2865.08
OpenAI: GPT-6 Astra ProOpenAI	1M	573.02	2865.08
Anthropic: Claude Opus 4.1Anthropic	200K	859.52	4297.61
OpenAI: o1OpenAI	200K	859.52	3438.09
OpenAI: o3 ProOpenAI	200K	1146.03	4584.12
OpenAI: GPT-5.2 ProOpenAI	400K	1203.33	9626.66
OpenAI: GPT-4OpenAI	8K	1719.05	3438.09
OpenAI: GPT-5.4 ProOpenAI	1M	1719.05	10314.28
OpenAI: GPT-5.5 ProOpenAI	1M	1719.05	10314.28
OpenAI: o1-proOpenAI	200K	8595.23	34380.92

Embedding models

25 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	0.29
all-minilm-l6-v2SBERT	512	0.29
all-mpnet-base-v2SBERT	512	0.29
bge-base-en-v1.5BAAI	512	0.29
clip-vit-b-32SBERT	77	0.29
clip-vit-b-32-multilingual-v1SBERT	512	0.29
e5-base-v2intfloat	512	0.29
gte-basethenlper	512	0.29
multi-qa-mpnet-base-dot-v1SBERT	512	0.29
paraphrase-minilm-l6-v2SBERT	512	0.29
text2vec-base-chineseshibing624	512	0.29
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	1.15

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	0.0115 EGP per 1024p image
flux-1-schnellblack-forest-labs	0.0287 EGP per 1024p image
p-imagePrunaAI	0.2865 EGP per image
flux-1-devblack-forest-labs	0.5157 EGP per 1024p image
ming-image-0.1-designinclusionAI	0.573 EGP per 1024p image
ming-image-0.1-design-layerinclusionAI	0.573 EGP per 1024p image
flux-2-klein-4bblack-forest-labs	0.8022 EGP per 1024p image
flux-2-klein-9bblack-forest-labs	0.8595 EGP per 1024p image
flux-2-problack-forest-labs	≈ 0.8595 EGP per image
flux-2-devblack-forest-labs	1.02 EGP per 1024p image
wan2.6-t2iWan-AI	1.72 EGP per image
nano-banana-2-liteGoogle	1.93 EGP per image
bria-3.2Bria	2.29 EGP per image
bria-3.2-vectorBria	2.29 EGP per image
fiboBria	2.29 EGP per image
fibo-1.5Bria	2.29 EGP per image
flux-1.1-problack-forest-labs	2.29 EGP per image
seedream-4ByteDance	2.29 EGP per image
seedream-4.5ByteDance	2.29 EGP per image
nano-banana-2Google	3.85 EGP per image
flux-2-maxblack-forest-labs	≈ 4.01 EGP per image
qwen-image-maxAlibaba	4.30 EGP per image
seedream-5.0-proByteDance	5.67 EGP per image
Google: Nano Banana Pro (Gemini 3 Pro Image)Google	7.70 EGP per image
nano-banana-proGoogle	7.70 EGP per image

Decision models

5 models

System One models on /v1/systemone. Priced on input tokens: the state plus your questions. The short typed answers they return carry no output charge on any decision model today.

Model	Context	Input EGP / 1M
Respan: Span-01respan	—	1.15
Jared Palmer: Kev 4Bjaredpalmer	8K	2.41
Together: Tev1 4B Experimentaltogethercomputer	33K	2.41
TypeSafe: Jev 1.13typesafe	32K	2.41
Upstage: Solar Decideupstage	524K	2.87

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.