Models

Claude Fable 5.1

anthropic/claude-fable-5-1

Cached input ₹24.78/M · Cache write ₹1,238.69/M (1-hour ₹1,981.90/M)

Context

10,00,000

Input ₹/M

₹990.95/M

Output ₹/M

₹4,954.74/M

Claude Haiku 4.5

anthropic/claude-haiku-4-5

Cached input ₹9.92/M · Cache write ₹123.87/M (1-hour ₹198.20/M)

Context

2,00,000

Input ₹/M

₹99.10/M

Output ₹/M

₹495.48/M

Claude Haiku 5.5

anthropic/claude-haiku-5-5

Cached input ₹1.00/M · Cache write ₹12.39/M (1-hour ₹19.83/M) · prompts of 1,00,001+ tokens: in ₹49.55/M · out ₹247.74/M

Context

10,00,000

Input ₹/M

₹9.92/M

Output ₹/M

₹49.55/M

Claude Opus 4.5

anthropic/claude-opus-4-5

Cached input ₹49.55/M · Cache write ₹619.35/M (1-hour ₹990.95/M)

Context

2,00,000

Input ₹/M

₹495.48/M

Output ₹/M

₹2,477.37/M

Claude Opus 4.8

anthropic/claude-opus-4-8

Cached input ₹49.55/M · Cache write ₹619.35/M (1-hour ₹990.95/M)

Context

10,00,000

Input ₹/M

₹495.48/M

Output ₹/M

₹2,477.37/M

Claude Opus 5

anthropic/claude-opus-5

Cached input ₹49.55/M · Cache write ₹619.35/M (1-hour ₹990.95/M)

Context

10,00,000

Input ₹/M

₹495.48/M

Output ₹/M

₹2,477.37/M

Claude Opus 5.5

anthropic/claude-opus-5-5

Cached input ₹19.83/M · Cache write ₹495.48/M (1-hour ₹792.77/M)

Context

10,00,000

Input ₹/M

₹396.39/M

Output ₹/M

₹1,981.90/M

Claude Sonnet 4.5

anthropic/claude-sonnet-4-5

Cached input ₹29.74/M · Cache write ₹371.61/M (1-hour ₹594.58/M)

Context

2,00,000

Input ₹/M

₹297.29/M

Output ₹/M

₹1,486.43/M

Claude Sonnet 4.6

anthropic/claude-sonnet-4-6

Cached input ₹29.74/M · Cache write ₹371.61/M (1-hour ₹594.58/M)

Context

10,00,000

Input ₹/M

₹297.29/M

Output ₹/M

₹1,486.43/M

Claude Sonnet 5

anthropic/claude-sonnet-5

Cached input ₹19.83/M · Cache write ₹247.74/M (1-hour ₹396.39/M)

Context

10,00,000

Input ₹/M

₹198.20/M

Output ₹/M

₹990.95/M

Claude Sonnet 5.5

anthropic/claude-sonnet-5-5

Cached input ₹9.92/M · Cache write ₹247.74/M (1-hour ₹396.39/M)

Context

10,00,000

Input ₹/M

₹198.20/M

Output ₹/M

₹990.95/M

DeepSeekFreemium

DeepSeek-OCR

deepseek-ai/deepseek-ocr

DeepSeek-OCR: document and image text recognition (images in, text/markdown out). Self-hosted in India. Recommended settings and quickstart: unoblox.ai/guide/deepseek-ocr

textimage

Context

8,192

Input ₹/M

₹2.69/M

Output ₹/M

₹8.96/M

DeepSeek R1 (0528)

deepseek-ai/deepseek-r1-0528

DeepSeek R1 (0528) reasoning model for math, coding and analytical tasks, served by Ogma via DeepInfra. Supports tool calling and structured outputs.

Context

1,63,840

Input ₹/M

₹49.55/M

Output ₹/M

₹213.06/M

Cached input ₹34.70/M

DeepSeek V3.2

deepseek-ai/deepseek-v3.2

Context

1,63,840

Input ₹/M

₹25.77/M

Output ₹/M

₹37.67/M

Cached input ₹12.89/M

DeepSeek V4 Flash

deepseek-ai/deepseek-v4-flash

Cached input ₹1.79/M · Cache write ₹11.16/M (1-hour ₹17.84/M)

Context

10,48,576

Input ₹/M

₹8.93/M

Output ₹/M

₹17.84/M

DeepSeek V4 Flash (0731)

deepseek-ai/deepseek-v4-flash-0731

Context

10,48,576

Input ₹/M

₹5.96/M

Output ₹/M

₹17.84/M

Cached input ₹1.50/M

DeepSeek V4 Pro (0813)

deepseek-ai/deepseek-v4-pro-0813

Context

10,48,576

Input ₹/M

₹128.83/M

Output ₹/M

₹257.65/M

Cached input ₹9.92/M

DeepSeek V4.1 Flash

deepseek-ai/deepseek-v4.1-flash

textimagereasoningtoolstext-generationreasoning

Context

10,48,576

Input ₹/M

₹13.89/M

Output ₹/M

₹41.63/M

Cached input ₹0.42/M

Google

Gemini 3.1 Pro Preview

google/gemini-3.1-pro-preview

Gemini 3.1 Pro Preview served by Ogma through Google Vertex AI. Promotional price: 50% off Google's standard Vertex AI price, including the long-context tier above 200K prompt tokens, for a limited period. Output billing includes reasoning tokens.

Context

10,48,576

Input ₹/M

~~Full price ₹198.20/M~~Now ₹99.10/M

Output ₹/M

~~Full price ₹1,189.15/M~~Now ₹594.58/M

50% off

Cached input ~~Full price ₹19.83/M~~Now ₹9.92/M · prompts of 2,00,001+ tokens: in ~~Full price ₹396.39/M~~Now ₹198.20/M · out ~~Full price ₹1,783.71/M~~Now ₹891.86/M

Google

Gemini 3.8 Flash

google/gemini-3.8-flash

Gemini 3.8 Flash served by Ogma through Google Vertex AI. Promotional price: 50% off Google's standard Vertex AI price, for a limited period. Output billing includes reasoning tokens.

textimagereasoningtoolstext-generationreasoning

Context

10,48,576

Input ₹/M

~~Full price ₹74.33/M~~Now ₹37.17/M

Output ₹/M

~~Full price ₹371.61/M~~Now ₹185.81/M

50% off

Cached input ~~Full price ₹7.44/M~~Now ₹3.72/M

GoogleFreemium

Gemma 4 26B A4B Instruct

google/gemma-4-26b-a4b-it

Context

2,62,144

Input ₹/M

₹3.75/M

Output ₹/M

₹19.71/M

Cached input ₹1.87/M

Google

Gemma 4 31B

google/gemma-4-31b-it

Gemma 4 31B. Paid model: ₹8.25 per 1M input tokens (₹4.58 cached) and ₹31.19 per 1M output tokens, including our 5% platform fee. Text and image input.

Context

2,62,144

Input ₹/M

₹8.06/M

Output ₹/M

₹30.48/M

Cached input ₹4.48/M

Llama 3.3 70B Instruct Turbo

meta-llama/llama-3.3-70b-instruct-turbo

Context

1,31,072

Input ₹/M

₹9.92/M

Output ₹/M

₹31.73/M

Llama 4 Scout

meta-llama/llama-4-scout-17b-16e-instruct

Context

3,27,680

Input ₹/M

₹9.92/M

Output ₹/M

₹29.74/M

Llama 3.1 8B Instruct Turbo

meta-llama/meta-llama-3.1-8b-instruct-turbo

text

Context

1,31,072

Input ₹/M

₹1.99/M

Output ₹/M

₹3.97/M

Muse Glimmer 30B

meta-models/muse-glimmer-30b

Context

1,31,072

Input ₹/M

₹29.74/M

Output ₹/M

₹118.93/M

Cached input ₹3.97/M

MiniMax

MiniMax M3

minimaxai/minimax-m3

Context

5,24,288

Input ₹/M

₹27.76/M

Output ₹/M

₹109.02/M

Cached input ₹5.56/M

Mistral AI

Mistral Nemo Instruct 2407

mistralai/mistral-nemo-instruct-2407

text

Context

1,31,072

Input ₹/M

₹2.88/M

Output ₹/M

₹2.99/M

Mistral AI

Mistral Small 3.2 24B

mistralai/mistral-small-3.2-24b-instruct-2506

Context

1,28,000

Input ₹/M

₹7.44/M

Output ₹/M

₹19.83/M

Moonshot AI

Kimi K3

moonshotai/kimi-k3

Cached input ₹28.25/M · Cache write ₹353.04/M (1-hour ₹564.85/M)

Context

10,48,576

Input ₹/M

₹282.43/M

Output ₹/M

₹1,412.11/M

GPT-4.1

openai/gpt-4.1

Context

10,47,576

Input ₹/M

₹198.20/M

Output ₹/M

₹792.77/M

Cached input ₹49.55/M

GPT-4.1 mini

openai/gpt-4.1-mini

Context

10,47,576

Input ₹/M

₹39.65/M

Output ₹/M

₹158.57/M

Cached input ₹9.92/M

GPT-4.1 nano

openai/gpt-4.1-nano

Context

10,47,576

Input ₹/M

₹9.92/M

Output ₹/M

₹39.65/M

Cached input ₹2.48/M

GPT-4o

openai/gpt-4o

Context

1,28,000

Input ₹/M

₹247.74/M

Output ₹/M

₹990.95/M

Cached input ₹123.87/M

GPT-4o mini

openai/gpt-4o-mini

Context

1,28,000

Input ₹/M

₹14.87/M

Output ₹/M

₹59.47/M

Cached input ₹7.44/M

GPT 5

openai/gpt-5

Context

4,00,000

Input ₹/M

₹123.87/M

Output ₹/M

₹990.95/M

Cached input ₹12.39/M

GPT 5-mini

openai/gpt-5-mini

Context

4,00,000

Input ₹/M

₹24.78/M

Output ₹/M

₹198.20/M

Cached input ₹2.48/M

GPT 5-nano

openai/gpt-5-nano

Context

4,00,000

Input ₹/M

₹4.96/M

Output ₹/M

₹39.65/M

Cached input ₹0.51/M

GPT 5.1

openai/gpt-5.1

Context

4,00,000

Input ₹/M

₹123.87/M

Output ₹/M

₹990.95/M

Cached input ₹12.39/M

GPT 5.2

openai/gpt-5.2

Context

4,00,000

Input ₹/M

₹173.42/M

Output ₹/M

₹1,387.34/M

Cached input ₹17.35/M

GPT 5.4

openai/gpt-5.4

Cached input ₹24.78/M · prompts of 2,72,001+ tokens: in ₹495.48/M · out ₹2,229.64/M

Context

4,00,000

Input ₹/M

₹247.74/M

Output ₹/M

₹1,486.43/M

GPT 5.4-mini

openai/gpt-5.4-mini

Context

4,00,000

Input ₹/M

₹74.33/M

Output ₹/M

₹445.94/M

Cached input ₹7.44/M

GPT 5.4-nano

openai/gpt-5.4-nano

Context

4,00,000

Input ₹/M

₹19.83/M

Output ₹/M

₹123.87/M

Cached input ₹1.99/M

GPT 5.5

openai/gpt-5.5

Cached input ₹49.55/M · prompts of 2,72,001+ tokens: in ₹990.95/M · out ₹4,459.27/M

Context

4,00,000

Input ₹/M

₹495.48/M

Output ₹/M

₹2,972.85/M

GPT 5.6-luna

openai/gpt-5.6-luna

Cached input ₹1.99/M · Cache write ₹24.78/M · prompts of 2,72,001+ tokens: in ₹39.65/M · out ₹178.38/M

Context

4,00,000

Input ₹/M

₹19.83/M

Output ₹/M

₹118.93/M

GPT 5.6-sol

openai/gpt-5.6-sol

Cached input ₹39.65/M · Cache write ₹495.48/M · prompts of 2,72,001+ tokens: in ₹792.77/M · out ₹2,972.85/M

Context

4,00,000

Input ₹/M

₹396.39/M

Output ₹/M

₹1,981.90/M

GPT 5.6-terra

openai/gpt-5.6-terra

Cached input ₹19.83/M · Cache write ₹247.74/M · prompts of 2,72,001+ tokens: in ₹396.39/M · out ₹1,783.71/M

Context

4,00,000

Input ₹/M

₹198.20/M

Output ₹/M

₹1,189.15/M

GPT 6-astra

openai/gpt-6-astra

Cached input ₹99.10/M · Cache write ₹1,238.69/M · prompts of 2,72,001+ tokens: in ₹1,981.90/M · out ₹7,432.11/M

Context

4,00,000

Input ₹/M

₹990.95/M

Output ₹/M

₹4,954.74/M

GPT 6 Luna

openai/gpt-6-luna

Cached input ₹1.00/M · Cache write ₹12.39/M · prompts of 2,72,001+ tokens: in ₹19.83/M · out ₹74.33/M

Context

10,50,000

Input ₹/M

₹9.92/M

Output ₹/M

₹49.55/M

GPT 6 Sol

openai/gpt-6-sol

Cached input ₹19.83/M · Cache write ₹247.74/M · prompts of 2,72,001+ tokens: in ₹396.39/M · out ₹1,486.43/M

Context

10,50,000

Input ₹/M

₹198.20/M

Output ₹/M

₹990.95/M

GPT 6.1 Sol

openai/gpt-6.1-sol

Cached input ₹9.92/M · Cache write ₹247.74/M · prompts of 2,72,001+ tokens: in ₹396.39/M · out ₹1,486.43/M

Context

10,50,000

Input ₹/M

₹198.20/M

Output ₹/M

₹990.95/M

OpenAIFreemiumOffline — not currently available

GPT-OSS 120B

openai/gpt-oss-120b

Context

1,31,072

Input ₹/M

₹2.69/M

Output ₹/M

₹13.44/M

gpt-oss 20B

openai/gpt-oss-20b

Context

1,31,072

Input ₹/M

₹2.99/M

Output ₹/M

₹13.89/M

O1

openai/o1

Context

2,00,000

Input ₹/M

₹1,486.43/M

Output ₹/M

₹5,945.69/M

Cached input ₹743.22/M

O3

openai/o3

Context

2,00,000

Input ₹/M

₹198.20/M

Output ₹/M

₹792.77/M

Cached input ₹49.55/M

O3 MINI

openai/o3-mini

Context

2,00,000

Input ₹/M

₹109.02/M

Output ₹/M

₹436.03/M

Cached input ₹54.51/M

O4 MINI

openai/o4-mini

QwenFreemiumOffline — not currently available

Context

2,00,000

Input ₹/M

₹109.02/M

Output ₹/M

₹436.03/M

Cached input ₹27.26/M

Qwen3 1.7B

qwen/qwen3-1.7b

Context

40,960

Input ₹/M

₹2.41/M

Output ₹/M

₹18.01/M

Qwen3 235B A22B

qwen/qwen3-235b-a22b-instruct-2507

Context

2,62,144

Input ₹/M

₹8.93/M

Output ₹/M

₹54.51/M

Qwen3 Max

qwen/qwen3-max

Cached input ₹23.80/M · prompts of 32,001+ tokens: in ₹237.84/M · out ₹1,189.15/M · prompts of 1,28,001+ tokens: in ₹297.29/M · out ₹1,486.43/M

Context

2,56,000

Input ₹/M

₹118.93/M

Output ₹/M

₹594.58/M

Qwen3 Next 80B A3B Instruct

qwen/qwen3-next-80b-a3b-instruct

Context

2,62,144

Input ₹/M

₹8.93/M

Output ₹/M

₹109.02/M

Qwen3 VL 235B A22B

qwen/qwen3-vl-235b-a22b-instruct

Context

2,62,144

Input ₹/M

₹19.83/M

Output ₹/M

₹87.22/M

Cached input ₹10.91/M

Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct

Context

2,62,144

Input ₹/M

₹14.87/M

Output ₹/M

₹59.47/M

Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

Context

2,62,144

Input ₹/M

₹44.60/M

Output ₹/M

₹297.29/M

Cached input ₹21.81/M

Qwen3.5 9B

qwen/qwen3.5-9b

Context

2,62,144

Input ₹/M

₹9.92/M

Output ₹/M

₹14.87/M

Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

textimagereasoningtoolstransformerssafetensors

Context

2,62,144

Input ₹/M

₹9.92/M

Output ₹/M

₹94.15/M

QwenFreemium

Qwen3.8-27B

qwen/qwen3.8-27b

Context

2,62,144

Input ₹/M

₹3.58/M

Output ₹/M

₹121.03/M

Cached input ₹1.61/M

7.5M downloads

Qwen3.8 Flash

qwen/qwen3.8-flash

Context

10,00,000

Input ₹/M

₹11.21/M

Output ₹/M

₹37.87/M

Cached input ₹1.41/M

Qwen3.8 Max

qwen/qwen3.8-max

Context

2,56,000

Input ₹/M

₹163.52/M

Output ₹/M

₹490.63/M

Cached input ₹20.43/M

StepFun

Step 5 Preview

stepfun-ai/step-5-preview

Context

10,48,576

Input ₹/M

₹99.10/M

Output ₹/M

₹267.57/M

Cached input ₹9.92/M

TypeSafeFreemium

TypeSafe jev

typesafe/jev

jev is TypeSafe systemone reasoning: state plus typed questions returns structured answers. Input-token billed (output free); launch pricing zero.

textSystem One

Context

64,000

Input ₹/M

₹0.00/M

Output ₹/M

₹0.00/M

Xiaomi MiMo

MiMo V2.6 Flash

xiaomimimo/mimo-v2.6-flash

Context

10,48,576

Input ₹/M

₹13.89/M

Output ₹/M

₹27.76/M

Cached input ₹0.29/M

Xiaomi MiMo

MiMo V2.6 Pro

xiaomimimo/mimo-v2.6-pro