Supported models

Model labels, pricing, Fast availability, token limits, and reasoning options available through Router.

This table uses concise model labels to make the catalog easier to scan. These display labels are not necessarily valid model values for API requests.

Check availability: GET /v1/models is authoritative for the exact callable request IDs available to the caller's key. Use those IDs as the model value in API requests.

  • Token limits reflect the currently published model specifications. These values can change, and deprecated models may be removed in the future.
  • Prices are base rates in USD per million tokens. Service tiers, long contexts, caching, and other features may use different rates.
  • Reasoning efforts are the exact values accepted by each model. Fast indicates that an accelerated tier is available; its pricing may differ from the base rates shown here.
  • Note that Gemini models currently require BYOK.

Available models

Compare pricing, context windows and capabilities across models → router.com/models

Model provider
Model
Input cost
Output cost
Fast mode
Context window
Maximum output
Reasoning efforts
$0.10
$0.50
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$1.00
$5.00
—
200,000
64,000
none, minimal, low, medium, high, xhigh
$2.00
$10.00
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$2.00
$10.00
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$3.00
$15.00
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$3.00
$15.00
—
200,000
64,000
none, minimal, low, medium, high, xhigh
$4.00
$20.00
Available
1,000,000
128,000
minimal, low, medium, high, xhigh, max
$5.00
$25.00
Available
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$5.00
$25.00
Available
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$5.00
$25.00
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$5.00
$25.00
—
1,000,000
128,000
none, minimal, low, medium, high, xhigh, max
$10.00
$50.00
—
1,000,000
128,000
minimal, low, medium, high, xhigh, max
$10.00
$50.00
—
1,000,000
128,000
minimal, low, medium, high, xhigh, max
$0.30
$1.20
—
1,048,576
32,768
high
$0.15
$0.50
—
1,048,576
131,072
high, max
Z.ai
zai-org/GLM-5.3
$1.40
$4.40
—
1,048,576
262,144
high, xhigh, max
$1.32
$3.96
—
1,048,576
384,000
high
$2.10
$6.60
—
1,048,576
1,048,576
high, xhigh, max
$0.13
$0.26
—
1,048,576
1,048,576
high
Z.ai
zai-org/GLM-5.2
$1.40
$4.40
—
1,048,576
1,048,576
high, xhigh, max
NVIDIA
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
$0.60
$2.40
—
202,800
202,800
none, medium, high
$0.10
$0.50
—
128,072
128,072
minimal, low, medium, high
$1.25
$4.25
—
1,048,576
1,048,576
low, medium, high, xhigh
$3.00
$15.00
—
1,048,576
1,048,576
minimal, low, medium, high, max
$0.30
$1.20
—
1,048,576
1,048,576
none, minimal, low, medium, high, xhigh
$0.15
$0.50
—
1,048,576
1,048,576
minimal, low, medium, high, xhigh, max
$1.40
$4.40
—
1,048,576
1,048,576
minimal, low, medium, high, xhigh, max
$0.05
$0.20
—
262,144
262,144
Not supported
$0.60
$2.40
—
262,144
262,144
none, minimal, low, medium, high, xhigh
$2.00
$6.00
—
1,000,000
131,072
none, minimal, low, medium, high, xhigh
$0.30
$1.20
—
512,000
512,000
none, minimal, low, medium, high, xhigh
$0.15
$0.60
—
131,072
131,072
minimal, low, medium, high, xhigh
$3.00
$15.00
—
1,048,576
1,048,576
minimal, low, medium, high, xhigh, max
$4.50
$22.50
—
1,048,576
1,048,576
minimal, low, medium, high, xhigh, max
$1.25
$4.25
—
1,048,576
1,048,576
low, medium, high, xhigh
Gemini
gemini-3.8-flash
$0.75
$3.75
—
1,048,576
65,536
low, medium, high
Gemini
gemini-3.7-flash
$0.75
$3.75
—
1,048,576
65,536
low, medium, high
Gemini
gemini-3.5-flash-lite
$0.30
$2.50
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-3.6-flash
$0.75
$3.75
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-3.5-flash
$1.50
$9.00
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-3.1-flash-lite
$0.25
$1.50
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-3.1-pro-preview
$2.00
$12.00
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-3-flash-preview
$0.50
$3.00
—
1,048,576
65,536
minimal, low, medium, high
Gemini
gemini-2.5-flash-lite
$0.10
$0.40
—
1,048,576
65,536
none, minimal, low, medium, high
Gemini
gemini-2.5-flash
$0.30
$2.50
—
1,048,576
65,536
none, minimal, low, medium, high
Gemini
gemini-2.5-pro
$1.25
$10.00
—
1,048,576
65,536
minimal, low, medium, high, xhigh
$4.00
$20.00
—
1,048,576
32,768
low, medium, high
$2.00
$10.00
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$0.10
$0.50
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$2.00
$10.00
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$10.00
$50.00
Available
1,050,000
128,000
low, medium, high, xhigh, max
$0.20
$1.20
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$2.00
$12.00
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$4.00
$20.00
Available
1,050,000
128,000
none, low, medium, high, xhigh, max
$30.00
$180.00
—
1,050,000
128,000
medium, high, xhigh
$5.00
$30.00
Available
1,050,000
128,000
none, low, medium, high, xhigh
$0.75
$4.50
Available
400,000
128,000
none, low, medium, high, xhigh
$0.20
$1.25
—
400,000
128,000
none, low, medium, high, xhigh
$2.50
$15.00
Available
1,050,000
128,000
none, low, medium, high, xhigh
$30.00
$180.00
—
1,050,000
128,000
medium, high, xhigh
$1.75
$14.00
—
400,000
128,000
none, low, medium, high, xhigh
$21.00
$168.00
—
400,000
128,000
medium, high, xhigh
$1.75
$14.00
Available
400,000
128,000
none, low, medium, high, xhigh
$1.25
$10.00
Available
400,000
128,000
none, low, medium, high
$15.00
$120.00
—
400,000
272,000
high
$0.05
$0.40
—
400,000
128,000
minimal, low, medium, high
$0.25
$2.00
Available
400,000
128,000
minimal, low, medium, high
$1.25
$10.00
Available
400,000
128,000
minimal, low, medium, high
$20.00
$80.00
—
200,000
100,000
low, medium, high
$2.00
$8.00
Available
200,000
100,000
low, medium, high
$0.40
$1.60
Available
1,047,576
32,768
Not supported
$2.00
$8.00
Available
1,047,576
32,768
Not supported
$0.15
$0.60
Available
128,000
16,384
Not supported
$2.50
$10.00
Available
128,000
16,384
Not supported
$0.04
$0.00
—
64,000
64,000
Not supported
$0.04
$0.00
—
65,536
65,536
Not supported
$2.00
$6.00
—
500,000
500,000
low, medium, high, xhigh
$2.00
$6.00
—
500,000
500,000
minimal, low, medium, high, xhigh
$2.00
$6.00
—
500,000
500,000
minimal, low, medium, high, xhigh
$1.25
$2.50
—
1,000,000
1,000,000
none, minimal, low, medium, high, xhigh
$1.00
$2.00
—
256,000
256,000
Not supported
$1.25
$2.50
—
1,000,000
1,000,000
Not supported
$1.25
$2.50
—
1,000,000
1,000,000
Not supported
$1.25
$2.50
—
1,000,000
1,000,000
none, minimal, low, medium, high, xhigh, max

Data retention: Some frontier models have additional provider-specific data retention policies. See the Router Privacy Notice for details.

Deprecated models

Baseten

Baseten Model APIs retirement: These provider-specific IDs are no longer callable through Router. Use GET /v1/models for available IDs. Requests are not automatically redirected.

Model
Input cost
Output cost
Fast mode
Context window
Maximum output
Reasoning efforts
baseten
thinkingmachines/inkling-small
$0.50
$1.20
—
1,048,576
1,048,576
high
baseten
thinkingmachines/inkling
$1.00
$4.05
—
1,048,576
1,048,576
high
Moonshot AI
moonshotai/Kimi-K2.7-Code
$0.95
$4.00
—
262,000
262,000
medium, high
DeepSeek
deepseek-ai/DeepSeek-V4-Pro
$1.74
$3.48
—
1,048,576
384,000
medium, high
Moonshot AI
moonshotai/Kimi-K2.6
$0.95
$4.00
—
262,000
262,000
none, medium, high
Z.ai
zai-org/GLM-4.7
$0.60
$2.20
—
200,000
200,000
Not supported

Fireworks

Deprecated: These models are deprecated; retired models are no longer requestable. Check Fireworks's deprecation guidance for details.

Model
Status
Input cost
Output cost
Fast mode
Context window
Maximum output
Reasoning efforts
DeepSeek
accounts/fireworks/models/deepseek-v4-pro-0813
Retired
$1.32
$3.96
—
1,048,576
384,000
none, minimal, low, medium, high, xhigh, max
DeepSeek
accounts/fireworks/models/deepseek-v4-flash-0731
Retired
$0.22
$0.66
—
1,048,576
1,048,576
none, minimal, low, medium, high, xhigh, max
DeepSeek
accounts/fireworks/models/deepseek-v4-flash
Retired
$0.14
$0.28
—
1,048,576
1,048,576
none, minimal, low, medium, high, xhigh, max
Deprecated
$1.74
$3.48
—
1,048,576
384,000
none, minimal, low, medium, high, xhigh, max
Z.ai
accounts/fireworks/models/glm-5p2
Retired
$1.40
$4.40
—
1,048,576
1,048,576
none, minimal, low, medium, high, xhigh, max
Z.ai
accounts/fireworks/routers/glm-5p2-fast
Retired
$2.10
$6.60
—
1,048,576
1,048,576
none, minimal, low, medium, high, xhigh, max
Moonshot AI
accounts/fireworks/models/kimi-k2p7-code
Retired
$0.95
$4.00
—
262,144
262,144
none, minimal, low, medium, high, xhigh
Deprecated
$1.90
$8.00
—
262,144
262,144
none, minimal, low, medium, high, xhigh
Moonshot AI
accounts/fireworks/models/kimi-k2p6
Retired
$0.95
$4.00
—
262,144
262,144
none, minimal, low, medium, high, xhigh
Deprecated
$2.00
$8.00
—
262,144
262,144
none, minimal, low, medium, high, xhigh
Deprecated
$0.40
$1.60
—
262,144
262,144
none, minimal, low, medium, high, xhigh
Deprecated
$0.30
$1.20
—
196,608
196,608
none, minimal, low, medium, high, xhigh
Deprecated
$0.07
$0.30
—
131,072
131,072
none, minimal, low, medium, high, xhigh

OpenAI

OpenAI deprecations: These models are deprecated. OpenAI's current schedule includes an October 23, 2026 shutdown for affected legacy models. Check the OpenAI API deprecations documentation for each model's latest migration guidance and shutdown date.

Model
Input cost
Output cost
Fast mode
Context window
Maximum output
Reasoning efforts
$0.10
$0.40
Available
1,047,576
32,768
Not supported
$1.10
$4.40
Available
200,000
100,000
low, medium, high
$1.10
$4.40
—
200,000
100,000
low, medium, high
$15.00
$60.00
—
200,000
100,000
low, medium, high
$10.00
$30.00
—
128,000
4,096
Not supported
$30.00
$60.00
—
8,192
8,192
Not supported
$0.50
$1.50
—
16,385
4,096
Not supported

For details about how Router handles request data, see the Router Privacy Notice.