МЭТР

Models and pricing

Current model usage prices in Mattr. All prices are in rubles.

Text rates are per 1 million tokens. Image billing units are shown separately. Total cost depends on the request, response and selected model.

Updated 16/09/2026, 11:47 · MSK · refreshed hourly

Text and reasoning 25

Model	Author	Context	Input	Output	Other rates
claude-fable-5.1 Output up to 128,000	AuthorAnthropic	Context1,000,000tokens	Input1,000 ₽per 1M tokens	Output5,000 ₽per 1M tokens	Details Cache read 25 ₽per 1M tokens Cache write 1,250 ₽per 1M tokens
claude-haiku-4.5 Output up to 64,000	AuthorAnthropic	Context200,000tokens	Input100 ₽per 1M tokens	Output500 ₽per 1M tokens	Details Cache read 10 ₽per 1M tokens Cache write 125 ₽per 1M tokens
claude-opus-5 Output up to 128,000	AuthorAnthropic	Context1,000,000tokens	Input500 ₽per 1M tokens	Output2,500 ₽per 1M tokens	Details Cache read 50 ₽per 1M tokens Cache write 625 ₽per 1M tokens
claude-sonnet-5 Output up to 128,000	AuthorAnthropic	Context1,000,000tokens	Input200 ₽per 1M tokens	Output1,000 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens Cache write 250 ₽per 1M tokens
deepseek-v4-flash Output up to 393,216	AuthorDeepSeek	Context1,000,000tokens	Input8.54 ₽per 1M tokens	Output17.08 ₽per 1M tokens	Details Cache read 1.708 ₽per 1M tokens
deepseek-v4-pro Output up to 384,000	AuthorDeepSeek	Context1,048,576tokens	Input98.34 ₽per 1M tokens	Output295.02 ₽per 1M tokens	Details Cache read 3.278 ₽per 1M tokens
deepseek-v4.1-flash Output up to 384,000	AuthorDeepSeek	Context1,048,576tokens	Input15 ₽per 1M tokens	Output60 ₽per 1M tokens	Details Cache read 0.3 ₽per 1M tokens
gemini-2.5-flash-lite Output up to 65,535	AuthorGoogle	Context1,048,576tokens	Input10 ₽per 1M tokens	Output40 ₽per 1M tokens	Details Cache read 1 ₽per 1M tokens Cache write 8.333333 ₽per 1M tokens
gemini-3.1-flash-lite Output up to 65,536	AuthorGoogle	Context1,048,576tokens	Input25 ₽per 1M tokens	Output150 ₽per 1M tokens	Details Cache read 2.5 ₽per 1M tokens Cache write 8.333333 ₽per 1M tokens
gemini-3.1-pro-preview Output up to 65,536	AuthorGoogle	Context1,048,576tokens	Input200 ₽per 1M tokens	Output1,200 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens Cache write 37.5 ₽per 1M tokens Cache readContext above 200,000 40 ₽per 1M tokens Cache writeContext above 200,000 25 ₽per 1M tokens InputContext above 200,000 400 ₽per 1M tokens OutputContext above 200,000 1,800 ₽per 1M tokens
gemini-3.8-flash Output up to 65,536	AuthorGoogle	Context1,048,576tokens	Input75 ₽per 1M tokens	Output375 ₽per 1M tokens	Details Cache read 7.5 ₽per 1M tokens Cache write 4.166667 ₽per 1M tokens
glm-4.7-flash Output up to 117,964	AuthorZ.ai	Context200,000tokens	Input6.05 ₽per 1M tokens	Output40 ₽per 1M tokens	Details Cache read 1 ₽per 1M tokens Cache write 0 ₽per 1M tokens
glm-5.2 Output up to 131,072	AuthorZ.ai	Context1,048,576tokens	Input68.32 ₽per 1M tokens	Output214.72 ₽per 1M tokens	Details Cache read 12.688 ₽per 1M tokens
glm-5.3 Output up to 943,717	AuthorZ.ai	Context1,310,720tokens	Input140 ₽per 1M tokens	Output440 ₽per 1M tokens	Details Cache read 26 ₽per 1M tokens
glm-5.3-flash Output up to 131,072	AuthorZ.ai	Context1,310,720tokens	Input15 ₽per 1M tokens	Output50 ₽per 1M tokens	Details Cache read 3 ₽per 1M tokens
gpt-5-mini Output up to 128,000	AuthorOpenAI	Context400,000tokens	Input25 ₽per 1M tokens	Output200 ₽per 1M tokens	Details Cache read 2.5 ₽per 1M tokens
gpt-5-nano Output up to 128,000	AuthorOpenAI	Context400,000tokens	Input5 ₽per 1M tokens	Output40 ₽per 1M tokens	Details Cache read 0.5 ₽per 1M tokens
gpt-5.6-luna Output up to 128,000	AuthorOpenAI	Context1,050,000tokens	Input20 ₽per 1M tokens	Output120 ₽per 1M tokens	Details Cache read 2 ₽per 1M tokens
gpt-5.6-sol Output up to 128,000	AuthorOpenAI	Context1,050,000tokens	Input200 ₽per 1M tokens	Output1,000 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens Cache write 250 ₽per 1M tokens Cache readContext above 272,000 40 ₽per 1M tokens Cache writeContext above 272,000 500 ₽per 1M tokens InputContext above 272,000 400 ₽per 1M tokens OutputContext above 272,000 1,500 ₽per 1M tokens
gpt-6-astra Output up to 128,000	AuthorOpenAI	Context1,050,000tokens	Input1,000 ₽per 1M tokens	Output5,000 ₽per 1M tokens	Details Cache read 100 ₽per 1M tokens Cache write 1,250 ₽per 1M tokens Cache readContext above 272,000 200 ₽per 1M tokens Cache writeContext above 272,000 2,500 ₽per 1M tokens InputContext above 272,000 2,000 ₽per 1M tokens OutputContext above 272,000 7,500 ₽per 1M tokens
grok-4.20 Output up to 1,800,000	AuthorxAI	Context2,000,000tokens	Input125 ₽per 1M tokens	Output250 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens
grok-4.3 Output up to 900,000	AuthorxAI	Context1,000,000tokens	Input125 ₽per 1M tokens	Output250 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens
grok-4.6 Output up to 450,000	AuthorxAI	Context500,000tokens	Input200 ₽per 1M tokens	Output600 ₽per 1M tokens	Details Cache read 50 ₽per 1M tokens
grok-build-0.1 Output up to 230,400	AuthorxAI	Context256,000tokens	Input100 ₽per 1M tokens	Output200 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens
MATTR Auto Output up to 8,192	AuthorVarious authors	Context1,000,000tokens	Billed at the automatically selected model’s rate

Image generation 6

Model	Author	Context	Input	Output	Other rates
gemini-2.5-flash-image Output up to 8,192	AuthorGoogle	Context32,768tokens	Input30 ₽per 1M tokens	Output3,000 ₽per 1M tokens	Details Cache read 3 ₽per 1M tokens Cache write 8.333333 ₽per 1M tokens Output 250 ₽per 1M tokens
gemini-3-pro-image Output up to 32,768	AuthorGoogle	Context131,072tokens	Input200 ₽per 1M tokens	Output12,000 ₽per 1M tokens	Details Cache read 20 ₽per 1M tokens Cache write 37.5 ₽per 1M tokens Output 1,200 ₽per 1M tokens
gemini-3.1-flash-lite-image Output up to 58,982	AuthorGoogle	Context65,536tokens	Input25 ₽per 1M tokens	Output3,000 ₽per 1M tokens	Details Output 150 ₽per 1M tokens
gpt-5-image-mini Output up to 128,000	AuthorOpenAI	Context400,000tokens	Input250 ₽per 1M tokens	Output800 ₽per 1M tokens	Details Cache read 25 ₽per 1M tokens Output 200 ₽per 1M tokens
gpt-5.4-image-2 Output up to 128,000	AuthorOpenAI	Context272,000tokens	Input800 ₽per 1M tokens	Output3,000 ₽per 1M tokens	Details Cache read 200 ₽per 1M tokens Output 1,500 ₽per 1M tokens
nano-banana Output up to 32,768	AuthorGoogle	Context131,072tokens	Input50 ₽per 1M tokens	Output6,000 ₽per 1M tokens	Details Output 300 ₽per 1M tokens

Embeddings 3

Model	Author	Context	Input	Output	Other rates
bge-m3	AuthorBAAI	Context8,194tokens	Input1 ₽per 1M tokens	Output—	—
qwen3-embedding-8b	AuthorQwen	Context—tokens	Pricing unavailable
text-embedding-3-small	AuthorOpenAI	Context8,192tokens	Input2 ₽per 1M tokens	Output—	—

Where a range is shown, the price depends on the request route. Special modes, additional tools and other data types may be billed separately.

Text and reasoning 25

claude-fable-5.1

claude-haiku-4.5

claude-opus-5

claude-sonnet-5

deepseek-v4-flash

deepseek-v4-pro

deepseek-v4.1-flash

gemini-2.5-flash-lite

gemini-3.1-flash-lite

gemini-3.1-pro-preview

gemini-3.8-flash

glm-4.7-flash

glm-5.2

glm-5.3

glm-5.3-flash

gpt-5-mini

gpt-5-nano

gpt-5.6-luna

gpt-5.6-sol

gpt-6-astra

grok-4.20

grok-4.3

grok-4.6

grok-build-0.1

MATTR Auto

Image generation 6

gemini-2.5-flash-image

gemini-3-pro-image

gemini-3.1-flash-lite-image

gpt-5-image-mini

gpt-5.4-image-2

nano-banana

Embeddings 3

bge-m3

qwen3-embedding-8b

text-embedding-3-small