The Unified AI Gateway
Integrate via our OpenAI‑compatible API to access Chat, Image Generation, Edits, TTS, STT, Embeddings, and more across top providers. Explore every capability in the Playground, and use the Web Chat for full conversational workflows — all with one key, one bill, and 50% lower prices.
OpenAI
Anthropic
Gemini
Fluxclaude-sonnet-4.5-20250929
$1.50/1M input tokens, $7.50/1M output tokens
deepseek-v3.2-exp
$0.14/1M input tokens, $0.20/1M output tokens
gemini-2.5-flash-lite-preview-09-2025
$0.05/1M input tokens, $0.20/1M output tokens
text-embedding-3-large
$0.04/1M tokens
glm-4.6
$0.30/1M input tokens, $1.10/1M output tokens
gemini-2.0-flash-001
$0.05/1M input tokens, $0.20/1M output tokens
gpt-4o-mini-2024-07-18
$0.07/1M input tokens, $0.30/1M output tokens
gpt-5-mini-2025-08-07
$0.13/1M input tokens, $1.00/1M output tokens
gpt-4o-2024-11-20
$1.25/1M input tokens, $5.00/1M output tokens
deepseek-chat-v3.1
$0.10/1M input tokens, $0.40/1M output tokens
qwen3-235b-a22b-thinking-2507
$0.07/1M input tokens, $0.30/1M output tokens
gemini-2.5-flash-image-preview
$0.15/1M input tokens, $1.25/1M output tokens
sonar
$0.50/1M input tokens, $0.50/1M output tokens
kimi-k2-0905
$0.07/1M input tokens, $1.24/1M output tokens
o4-mini-2025-04-16
$0.55/1M input tokens, $2.20/1M output tokens
grok-4-0709
$2.25/1M input tokens, $11.25/1M output tokens
sdxl
~$0.0025/image
gpt-5-nano-2025-08-07
$0.02/1M input tokens, $0.20/1M output tokens
chatgpt-4o-latest
$2.50/1M input tokens, $7.50/1M output tokens
flux-1-kontext-pro
~$0.02/image
gemini-2.5-flash-preview-09-2025
$0.15/1M input tokens, $1.25/1M output tokens
claude-opus-4-20250514
$10.00/1M input tokens, $50.00/1M output tokens
venice-uncensored
$0.10/1M input tokens, $0.45/1M output tokens
claude-3.7-sonnet-20250219
$1.50/1M input tokens, $7.50/1M output tokens
flux-1-kontext-max
~$0.04/image
qwen3-coder
$0.15/1M input tokens, $0.60/1M output tokens
flux-1.1-pro-ultra
~$0.03/image
deepseek-chat-v3.1-terminus
$0.14/1M input tokens, $0.50/1M output tokens
qwen3-coder-plus
$0.50/1M input tokens, $0.90/1M output tokens
kandinsky-3.1
~$0.0050/image
whisper-large-v3
~$0.0008/minute
scribe-v1
~$0.0025/minute
llama-3.3-70b-instruct
$0.29/1M input tokens, $0.39/1M output tokens
flux-1.1-pro
~$0.04/image
imagen-4
~$0.03/image
imagen-3
~$0.03/image
whisper-large-v3-turbo
~$0.0001/minute
magistral-medium-2506
$1.00/1M input tokens, $2.50/1M output tokens
codex-mini
$0.75/1M input tokens, $3.00/1M output tokens
qwen3-vl-235b-a22b-thinking
$0.35/1M input tokens, $4.20/1M output tokens
qwen3-next-80b-a3b-instruct
$0.07/1M input tokens, $0.70/1M output tokens
gpt-4o-transcribe
~$0.0052/minute
llama-4-maverick-17b-128e-instruct
$0.28/1M input tokens, $1.10/1M output tokens
gpt-4o-2024-05-13
$2.50/1M input tokens, $7.50/1M output tokens
ideogram-v2-turbo
~$0.03/image
sonar-reasoning-pro
$1.00/1M input tokens, $4.00/1M output tokens
qwen-image
~$0.01/image
gemma-3-27b-it
$0.05/1M input tokens, $0.10/1M output tokens
mistral-medium-2505
$0.20/1M input tokens, $1.00/1M output tokens
o1-mini-2024-09-12
$1.50/1M input tokens, $6.00/1M output tokens
gemini-2.0-flash-lite-001
$0.04/1M input tokens, $0.15/1M output tokens
mistral-small-2501
$0.05/1M input tokens, $0.15/1M output tokens
magistral-small-2509
$0.25/1M input tokens, $0.75/1M output tokens
qwen3-235b-a22b
$0.05/1M input tokens, $0.30/1M output tokens
qwq-32b
$0.14/1M input tokens, $0.20/1M output tokens
qwen3-14b
$0.04/1M input tokens, $0.12/1M output tokens
llama-3-8b-instruct
$0.07/1M input tokens, $0.10/1M output tokens
mythomax-l2-13b
$0.03/1M input tokens, $0.03/1M output tokens
llama-3.2-1b-instruct
$0.02/1M input tokens, $0.02/1M output tokens
llama-3.1-8b-instruct
$0.05/1M input tokens, $0.05/1M output tokens
pixtral-large-2411
$1.00/1M input tokens, $3.00/1M output tokens
claude-3-opus-20240229
$7.50/1M input tokens, $37.50/1M output tokens
qwen-turbo
$0.02/1M input tokens, $0.10/1M output tokens
mistral-small-2506
$0.05/1M input tokens, $0.15/1M output tokens
qwen-max
$0.80/1M input tokens, $3.20/1M output tokens
phi-4
$0.04/1M input tokens, $0.07/1M output tokens
deepseek-prover-v2
$0.35/1M input tokens, $1.25/1M output tokens
codestral-2501
$0.15/1M input tokens, $0.45/1M output tokens
gpt-4-1106-preview
$5.00/1M input tokens, $15.00/1M output tokens
command-a-03-2025
$1.25/1M input tokens, $5.00/1M output tokens
llama-3.2-11b-vision-instruct
$0.10/1M input tokens, $0.10/1M output tokens
llama-3.1-70b-instruct
$0.30/1M input tokens, $0.40/1M output tokens
flux-1-pro
~$0.02/image
dall-e-3
~$0.04/image
mistral-moderation-2411
$0.05/1M tokens
eleven-multilingual-v1
~$0.03/1k chars
eleven-monolingual-v1
~$0.03/1k chars
claude-sonnet-4.5-20250929
$1.50/1M input tokens, $7.50/1M output tokens
deepseek-v3.2-exp
$0.14/1M input tokens, $0.20/1M output tokens
gemini-2.5-flash-lite-preview-09-2025
$0.05/1M input tokens, $0.20/1M output tokens
text-embedding-3-large
$0.04/1M tokens
glm-4.6
$0.30/1M input tokens, $1.10/1M output tokens
gemini-2.0-flash-001
$0.05/1M input tokens, $0.20/1M output tokens
gpt-4o-mini-2024-07-18
$0.07/1M input tokens, $0.30/1M output tokens
gpt-5-mini-2025-08-07
$0.13/1M input tokens, $1.00/1M output tokens
gpt-4o-2024-11-20
$1.25/1M input tokens, $5.00/1M output tokens
deepseek-chat-v3.1
$0.10/1M input tokens, $0.40/1M output tokens
qwen3-235b-a22b-thinking-2507
$0.07/1M input tokens, $0.30/1M output tokens
gemini-2.5-flash-image-preview
$0.15/1M input tokens, $1.25/1M output tokens
sonar
$0.50/1M input tokens, $0.50/1M output tokens
kimi-k2-0905
$0.07/1M input tokens, $1.24/1M output tokens
o4-mini-2025-04-16
$0.55/1M input tokens, $2.20/1M output tokens
grok-4-0709
$2.25/1M input tokens, $11.25/1M output tokens
sdxl
~$0.0025/image
gpt-5-nano-2025-08-07
$0.02/1M input tokens, $0.20/1M output tokens
chatgpt-4o-latest
$2.50/1M input tokens, $7.50/1M output tokens
flux-1-kontext-pro
~$0.02/image
gemini-2.5-flash-preview-09-2025
$0.15/1M input tokens, $1.25/1M output tokens
claude-opus-4-20250514
$10.00/1M input tokens, $50.00/1M output tokens
venice-uncensored
$0.10/1M input tokens, $0.45/1M output tokens
claude-3.7-sonnet-20250219
$1.50/1M input tokens, $7.50/1M output tokens
flux-1-kontext-max
~$0.04/image
qwen3-coder
$0.15/1M input tokens, $0.60/1M output tokens
flux-1.1-pro-ultra
~$0.03/image
deepseek-chat-v3.1-terminus
$0.14/1M input tokens, $0.50/1M output tokens
qwen3-coder-plus
$0.50/1M input tokens, $0.90/1M output tokens
kandinsky-3.1
~$0.0050/image
whisper-large-v3
~$0.0008/minute
scribe-v1
~$0.0025/minute
llama-3.3-70b-instruct
$0.29/1M input tokens, $0.39/1M output tokens
flux-1.1-pro
~$0.04/image
imagen-4
~$0.03/image
imagen-3
~$0.03/image
whisper-large-v3-turbo
~$0.0001/minute
magistral-medium-2506
$1.00/1M input tokens, $2.50/1M output tokens
codex-mini
$0.75/1M input tokens, $3.00/1M output tokens
qwen3-vl-235b-a22b-thinking
$0.35/1M input tokens, $4.20/1M output tokens
qwen3-next-80b-a3b-instruct
$0.07/1M input tokens, $0.70/1M output tokens
gpt-4o-transcribe
~$0.0052/minute
llama-4-maverick-17b-128e-instruct
$0.28/1M input tokens, $1.10/1M output tokens
gpt-4o-2024-05-13
$2.50/1M input tokens, $7.50/1M output tokens
ideogram-v2-turbo
~$0.03/image
sonar-reasoning-pro
$1.00/1M input tokens, $4.00/1M output tokens
qwen-image
~$0.01/image
gemma-3-27b-it
$0.05/1M input tokens, $0.10/1M output tokens
mistral-medium-2505
$0.20/1M input tokens, $1.00/1M output tokens
o1-mini-2024-09-12
$1.50/1M input tokens, $6.00/1M output tokens
gemini-2.0-flash-lite-001
$0.04/1M input tokens, $0.15/1M output tokens
mistral-small-2501
$0.05/1M input tokens, $0.15/1M output tokens
magistral-small-2509
$0.25/1M input tokens, $0.75/1M output tokens
qwen3-235b-a22b
$0.05/1M input tokens, $0.30/1M output tokens
qwq-32b
$0.14/1M input tokens, $0.20/1M output tokens
qwen3-14b
$0.04/1M input tokens, $0.12/1M output tokens
llama-3-8b-instruct
$0.07/1M input tokens, $0.10/1M output tokens
mythomax-l2-13b
$0.03/1M input tokens, $0.03/1M output tokens
llama-3.2-1b-instruct
$0.02/1M input tokens, $0.02/1M output tokens
llama-3.1-8b-instruct
$0.05/1M input tokens, $0.05/1M output tokens
pixtral-large-2411
$1.00/1M input tokens, $3.00/1M output tokens
claude-3-opus-20240229
$7.50/1M input tokens, $37.50/1M output tokens
qwen-turbo
$0.02/1M input tokens, $0.10/1M output tokens
mistral-small-2506
$0.05/1M input tokens, $0.15/1M output tokens
qwen-max
$0.80/1M input tokens, $3.20/1M output tokens
phi-4
$0.04/1M input tokens, $0.07/1M output tokens
deepseek-prover-v2
$0.35/1M input tokens, $1.25/1M output tokens
codestral-2501
$0.15/1M input tokens, $0.45/1M output tokens
gpt-4-1106-preview
$5.00/1M input tokens, $15.00/1M output tokens
command-a-03-2025
$1.25/1M input tokens, $5.00/1M output tokens
llama-3.2-11b-vision-instruct
$0.10/1M input tokens, $0.10/1M output tokens
llama-3.1-70b-instruct
$0.30/1M input tokens, $0.40/1M output tokens
flux-1-pro
~$0.02/image
dall-e-3
~$0.04/image
mistral-moderation-2411
$0.05/1M tokens
eleven-multilingual-v1
~$0.03/1k chars
eleven-monolingual-v1
~$0.03/1k chars
text-embedding-3-small
$0.0067/1M tokens
gpt-oss-120b
$0.07/1M input tokens, $0.30/1M output tokens
gpt-4.1-2025-04-14
$1.00/1M input tokens, $4.00/1M output tokens
gpt-5-2025-08-07
$0.63/1M input tokens, $5.00/1M output tokens
deepseek-chat-0324
$0.07/1M input tokens, $0.14/1M output tokens
gpt-4.1-mini-2025-04-14
$0.20/1M input tokens, $0.80/1M output tokens
gemini-embedding-001
$0.07/1M tokens
grok-4-fast-reasoning
$0.10/1M input tokens, $0.25/1M output tokens
gemini-2.5-flash
$0.15/1M input tokens, $1.25/1M output tokens
gemini-2.5-pro
$0.94/1M input tokens, $6.25/1M output tokens
claude-sonnet-4-20250514
$1.50/1M input tokens, $7.50/1M output tokens
gpt-5-codex
$0.63/1M input tokens, $5.00/1M output tokens
claude-opus-4.1-20250805
$10.00/1M input tokens, $50.00/1M output tokens
gpt-5-chat-latest
$0.63/1M input tokens, $5.00/1M output tokens
claude-3.5-sonnet-20241022
$1.50/1M input tokens, $7.50/1M output tokens
o3-2025-04-16
$1.00/1M input tokens, $4.00/1M output tokens
deepseek-reasoner-0528
$0.28/1M input tokens, $1.10/1M output tokens
gpt-4.1-nano-2025-04-14
$0.05/1M input tokens, $0.20/1M output tokens
grok-code-fast-1-0825
$0.10/1M input tokens, $0.75/1M output tokens
kimi-k2
$0.29/1M input tokens, $1.15/1M output tokens
sonar-deep-research
$1.00/1M input tokens, $4.00/1M output tokens
gpt-oss-20b
$0.02/1M input tokens, $0.10/1M output tokens
grok-3
$1.50/1M input tokens, $7.50/1M output tokens
grok-4-fast-non-reasoning
$0.10/1M input tokens, $0.25/1M output tokens
nova-micro-v1
$0.02/1M input tokens, $0.07/1M output tokens
flux-1-schnell
~$0.0015/image
claude-3.5-haiku-20241022
$0.40/1M input tokens, $2.00/1M output tokens
gpt-image-1
~$0.04/image
qwen3-235b-a22b-2507
$0.07/1M input tokens, $0.42/1M output tokens
open-mistral-nemo-2407
$0.02/1M input tokens, $0.04/1M output tokens
qwen-image-edit-2509
~$0.04/image
llama-4-scout-17b-16e-instruct
$0.24/1M input tokens, $0.96/1M output tokens
sonar-reasoning
$0.50/1M input tokens, $2.50/1M output tokens
minimax-m1
$0.40/1M input tokens, $0.96/1M output tokens
flux-1-krea-dev
~$0.01/image
midjourney
~$0.0080/image
grok-2-aurora
~$0.04/image
flux-1-dev
~$0.01/image
glm-4.5
$0.20/1M input tokens, $0.83/1M output tokens
gpt-4o-mini-tts
~$0.0076/1k chars
qwen3-max
$0.60/1M input tokens, $3.00/1M output tokens
mistral-small-2503
$0.05/1M input tokens, $0.15/1M output tokens
gpt-4-0613
$15.00/1M input tokens, $30.00/1M output tokens
recraft-v3
~$0.02/image
stable-diffusion-3.5-large
~$0.04/image
nova-lite-v1
$0.03/1M input tokens, $0.12/1M output tokens
nova-pro-v1
$0.40/1M input tokens, $1.60/1M output tokens
eleven-multilingual-v2
~$0.03/1k chars
qwen3-30b-a3b
$0.05/1M input tokens, $0.15/1M output tokens
llama-guard-4-12b
$0.02/1M input tokens, $0.02/1M output tokens
qwen3-32b
$0.05/1M input tokens, $0.15/1M output tokens
gpt-4o-search-preview-2025-03-11
$1.25/1M input tokens, $5.00/1M output tokens
ministral-8b-2410
$0.05/1M input tokens, $0.05/1M output tokens
qwen3-next-80b-a3b-thinking
$0.07/1M input tokens, $0.70/1M output tokens
o3-mini-2025-01-31
$0.55/1M input tokens, $2.20/1M output tokens
gpt-4o-2024-08-06
$1.25/1M input tokens, $5.00/1M output tokens
o1-2024-12-17
$7.50/1M input tokens, $30.00/1M output tokens
sonar-pro
$1.50/1M input tokens, $7.50/1M output tokens
wizardlm-2-8x22b
$0.25/1M input tokens, $0.25/1M output tokens
llama-3.1-405b-instruct
$1.50/1M input tokens, $1.50/1M output tokens
llama-3.2-3b-instruct
$0.02/1M input tokens, $0.02/1M output tokens
mistral-large-2411
$1.00/1M input tokens, $3.00/1M output tokens
claude-3-haiku-20240307
$0.13/1M input tokens, $0.63/1M output tokens
qwen-2.5-72b-instruct
$0.07/1M input tokens, $0.20/1M output tokens
mistral-saba-2502
$0.10/1M input tokens, $0.30/1M output tokens
grok-3-mini
$0.15/1M input tokens, $0.25/1M output tokens
qwen3-vl-235b-a22b-instruct
$0.35/1M input tokens, $1.40/1M output tokens
gpt-4-0125-preview
$5.00/1M input tokens, $15.00/1M output tokens
gpt-4-turbo-2024-04-09
$5.00/1M input tokens, $15.00/1M output tokens
grok-2-vision-1212
$1.00/1M input tokens, $5.00/1M output tokens
omni-moderation-2024-09-26
Free
llama-3-70b-instruct
$0.42/1M input tokens, $0.44/1M output tokens
stable-diffusion-3-large
~$0.04/image
text-embedding-ada-002
$0.03/1M tokens
eleven-v3
~$0.03/1k chars
eleven-turbo-v2
~$0.03/1k chars
text-embedding-3-small
$0.0067/1M tokens
gpt-oss-120b
$0.07/1M input tokens, $0.30/1M output tokens
gpt-4.1-2025-04-14
$1.00/1M input tokens, $4.00/1M output tokens
gpt-5-2025-08-07
$0.63/1M input tokens, $5.00/1M output tokens
deepseek-chat-0324
$0.07/1M input tokens, $0.14/1M output tokens
gpt-4.1-mini-2025-04-14
$0.20/1M input tokens, $0.80/1M output tokens
gemini-embedding-001
$0.07/1M tokens
grok-4-fast-reasoning
$0.10/1M input tokens, $0.25/1M output tokens
gemini-2.5-flash
$0.15/1M input tokens, $1.25/1M output tokens
gemini-2.5-pro
$0.94/1M input tokens, $6.25/1M output tokens
claude-sonnet-4-20250514
$1.50/1M input tokens, $7.50/1M output tokens
gpt-5-codex
$0.63/1M input tokens, $5.00/1M output tokens
claude-opus-4.1-20250805
$10.00/1M input tokens, $50.00/1M output tokens
gpt-5-chat-latest
$0.63/1M input tokens, $5.00/1M output tokens
claude-3.5-sonnet-20241022
$1.50/1M input tokens, $7.50/1M output tokens
o3-2025-04-16
$1.00/1M input tokens, $4.00/1M output tokens
deepseek-reasoner-0528
$0.28/1M input tokens, $1.10/1M output tokens
gpt-4.1-nano-2025-04-14
$0.05/1M input tokens, $0.20/1M output tokens
grok-code-fast-1-0825
$0.10/1M input tokens, $0.75/1M output tokens
kimi-k2
$0.29/1M input tokens, $1.15/1M output tokens
sonar-deep-research
$1.00/1M input tokens, $4.00/1M output tokens
gpt-oss-20b
$0.02/1M input tokens, $0.10/1M output tokens
grok-3
$1.50/1M input tokens, $7.50/1M output tokens
grok-4-fast-non-reasoning
$0.10/1M input tokens, $0.25/1M output tokens
nova-micro-v1
$0.02/1M input tokens, $0.07/1M output tokens
flux-1-schnell
~$0.0015/image
claude-3.5-haiku-20241022
$0.40/1M input tokens, $2.00/1M output tokens
gpt-image-1
~$0.04/image
qwen3-235b-a22b-2507
$0.07/1M input tokens, $0.42/1M output tokens
open-mistral-nemo-2407
$0.02/1M input tokens, $0.04/1M output tokens
qwen-image-edit-2509
~$0.04/image
llama-4-scout-17b-16e-instruct
$0.24/1M input tokens, $0.96/1M output tokens
sonar-reasoning
$0.50/1M input tokens, $2.50/1M output tokens
minimax-m1
$0.40/1M input tokens, $0.96/1M output tokens
flux-1-krea-dev
~$0.01/image
midjourney
~$0.0080/image
grok-2-aurora
~$0.04/image
flux-1-dev
~$0.01/image
glm-4.5
$0.20/1M input tokens, $0.83/1M output tokens
gpt-4o-mini-tts
~$0.0076/1k chars
qwen3-max
$0.60/1M input tokens, $3.00/1M output tokens
mistral-small-2503
$0.05/1M input tokens, $0.15/1M output tokens
gpt-4-0613
$15.00/1M input tokens, $30.00/1M output tokens
recraft-v3
~$0.02/image
stable-diffusion-3.5-large
~$0.04/image
nova-lite-v1
$0.03/1M input tokens, $0.12/1M output tokens
nova-pro-v1
$0.40/1M input tokens, $1.60/1M output tokens
eleven-multilingual-v2
~$0.03/1k chars
qwen3-30b-a3b
$0.05/1M input tokens, $0.15/1M output tokens
llama-guard-4-12b
$0.02/1M input tokens, $0.02/1M output tokens
qwen3-32b
$0.05/1M input tokens, $0.15/1M output tokens
gpt-4o-search-preview-2025-03-11
$1.25/1M input tokens, $5.00/1M output tokens
ministral-8b-2410
$0.05/1M input tokens, $0.05/1M output tokens
qwen3-next-80b-a3b-thinking
$0.07/1M input tokens, $0.70/1M output tokens
o3-mini-2025-01-31
$0.55/1M input tokens, $2.20/1M output tokens
gpt-4o-2024-08-06
$1.25/1M input tokens, $5.00/1M output tokens
o1-2024-12-17
$7.50/1M input tokens, $30.00/1M output tokens
sonar-pro
$1.50/1M input tokens, $7.50/1M output tokens
wizardlm-2-8x22b
$0.25/1M input tokens, $0.25/1M output tokens
llama-3.1-405b-instruct
$1.50/1M input tokens, $1.50/1M output tokens
llama-3.2-3b-instruct
$0.02/1M input tokens, $0.02/1M output tokens
mistral-large-2411
$1.00/1M input tokens, $3.00/1M output tokens
claude-3-haiku-20240307
$0.13/1M input tokens, $0.63/1M output tokens
qwen-2.5-72b-instruct
$0.07/1M input tokens, $0.20/1M output tokens
mistral-saba-2502
$0.10/1M input tokens, $0.30/1M output tokens
grok-3-mini
$0.15/1M input tokens, $0.25/1M output tokens
qwen3-vl-235b-a22b-instruct
$0.35/1M input tokens, $1.40/1M output tokens
gpt-4-0125-preview
$5.00/1M input tokens, $15.00/1M output tokens
gpt-4-turbo-2024-04-09
$5.00/1M input tokens, $15.00/1M output tokens
grok-2-vision-1212
$1.00/1M input tokens, $5.00/1M output tokens
omni-moderation-2024-09-26
Free
llama-3-70b-instruct
$0.42/1M input tokens, $0.44/1M output tokens
stable-diffusion-3-large
~$0.04/image
text-embedding-ada-002
$0.03/1M tokens
eleven-v3
~$0.03/1k chars
eleven-turbo-v2
~$0.03/1k chars
Why choose NagaAI?
Everything you need to build with AI, unified in one platform
One API, Many Models
Hundreds of models from top startups. Chat, images, TTS, embeddings — unified in one interface.
Transparent Pricing
Simple pay-as-you-go. Pay only for usage with no hidden fees or commitments.
OpenAI Compatible
Drop-in OpenAI replacement. Switch in minutes with just a URL change.
Affordable & Reliable
50% lower costs with enterprise-grade reliability and 99.9% uptime.
Explore available models
Choose from our comprehensive selection of AI capabilities
Trusted by developers worldwide
Join thousands building the future of AI applications
Join the NagaAI Community
Connect with developers, suggest features, report bugs, and shape the future of unified AI infrastructure.