Skip to content

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Rust
12.7 KB
Raw Blame
# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0

# Rates are USD per million text tokens. Each group lists the exact IDs that share its rates.
# Groups expand into individual model lookups when this file is loaded.
# These defaults stay fixed until Switchyard is updated; an override replaces this table.
# Estimates exclude service tiers, long-context premiums, tools, and time-based cache storage.
# OpenAI cache-write rates cover 30-minute retention, not 12-hour retention.

# OpenRouter IDs in this file use the advertised token rates from 2026-10-21.
# https://openrouter.ai/api/v1/models
# OpenRouter rates can differ from direct-provider rates and can change with the selected provider.
# This table uses the input rate for OpenRouter cache reads without a published discount.
# This table uses the input rate for OpenRouter cache writes without a separate fee.
# OpenRouter's Google cache-write fields describe time-based storage.
# This table uses the input rate for those Google cache writes.
# This table excludes long-context, service-tier, and time-of-day adjustments.

# OpenAI's standard short-context rates were checked on 2026-10-21.
# https://developers.openai.com/api/docs/pricing
# GPT-5.6 and newer use the default 30-minute cache-write rate.
# codex-auto-review uses the gpt-6-sol rates for cost and baseline estimates.
# Gateway estimates use list rates where shown; a reported charge takes precedence.
# Older models have no extra write fee, so separately counted writes use the input rate.

[[prices]]
models = ["gpt-6-astra", "openai/gpt-6-astra", "openai/gpt-6-astra-pro"]
input = 10
output = 50
cache_read = 1
cache_write = 12.5

[[prices]]
models = ["gpt-6.1-sol", "openai/gpt-6.1-sol", "openai/gpt-6.1-sol-pro"]
input = 2
output = 10
cache_read = 0.1
cache_write = 2.5

[[prices]]
models = ["gpt-6-sol", "codex-auto-review", "openai/gpt-6-sol", "openai/gpt-6-sol-pro"]
input = 2
output = 10
cache_read = 0.2
cache_write = 2.5

[[prices]]
models = ["gpt-6-luna", "openai/gpt-6-luna", "openai/gpt-6-luna-pro"]
input = 0.1
output = 0.5
cache_read = 0.01
cache_write = 0.125

[[prices]]
models = ["gpt-5.6-sol", "openai/gpt-5.6-sol", "openrouter/openai/gpt-5.6-sol"]
input = 4
output = 20
cache_read = 0.4
cache_write = 5

[[prices]]
models = ["gpt-5.6-luna", "openai/gpt-5.6-luna"]
input = 0.2
output = 1.2
cache_read = 0.02
cache_write = 0.25

[[prices]]
models = ["gpt-5.6-terra", "openai/gpt-5.6-terra", "openrouter/openai/gpt-5.6-terra"]
input = 2
output = 12
cache_read = 0.2
cache_write = 2.5

[[prices]]
models = ["gpt-5.5", "openai/gpt-5.5", "azure/openai/gpt-5.5"]
input = 5
output = 30
cache_read = 0.5
cache_write = 5

[[prices]]
models = ["gpt-5.4-mini"]
input = 0.75
output = 4.5
cache_read = 0.075
cache_write = 0.75

[[prices]]
models = ["gpt-5.4-nano"]
input = 0.2
output = 1.25
cache_read = 0.02
cache_write = 0.2

[[prices]]
models = ["gpt-5.2", "openai/gpt-5.2"]
input = 1.75
output = 14
cache_read = 0.175
cache_write = 1.75

[[prices]]
models = ["gpt-4.1", "o3"]
input = 2
output = 8
cache_read = 0.5
cache_write = 2

[[prices]]
models = ["gpt-4.1-mini"]
input = 0.4
output = 1.6
cache_read = 0.1
cache_write = 0.4

[[prices]]
models = ["o4-mini"]
input = 1.1
output = 4.4
cache_read = 0.275
cache_write = 1.1

# Anthropic's standard token rates were checked on 2026-10-21.
# https://platform.claude.com/docs/en/about-claude/pricing
# The cache_write field uses the five-minute rate.
# The cache_write_1h field uses the one-hour rate.

[[prices]]
models = ["claude-sonnet-5", "anthropic/claude-sonnet-5"]
input = 2
output = 10
cache_read = 0.2
cache_write = 2.5
cache_write_1h = 4

[[prices]]
models = ["claude-sonnet-5-5", "anthropic/claude-sonnet-5.5"]
input = 2
output = 10
cache_read = 0.1
cache_write = 2.5
cache_write_1h = 4

[[prices]]
models = ["claude-opus-5-5", "anthropic/claude-opus-5.5"]
input = 4
output = 20
cache_read = 0.2
cache_write = 5
cache_write_1h = 8

[[prices]]
models = [
    "claude-opus-4-7",
    "anthropic/claude-opus-4.7",
    "claude-opus-4-8",
    "anthropic/claude-opus-4.8",
    "claude-opus-5",
    "anthropic/claude-opus-5",
    "claude-opus-4-6",
    "anthropic/claude-opus-4.6",
]
input = 5
output = 25
cache_read = 0.5
cache_write = 6.25
cache_write_1h = 10

[[prices]]
models = [
    "claude-haiku-4-5",
    "claude-haiku-4-5-20251001",
    "anthropic/claude-haiku-4.5",
    "azure/anthropic/claude-haiku-4-5",
]
input = 1
output = 5
cache_read = 0.1
cache_write = 1.25
cache_write_1h = 2

[[prices]]
models = ["claude-fable-5", "anthropic/claude-fable-5"]
input = 10
output = 50
cache_read = 1
cache_write = 12.5
cache_write_1h = 20

[[prices]]
models = ["claude-fable-5-1", "anthropic/claude-fable-5.1"]
input = 10
output = 50
cache_read = 0.25
cache_write = 12.5
cache_write_1h = 20

# Haiku 5.5 rates apply up to 100,000 prompt tokens. Longer prompts cost five times more.

[[prices]]
models = ["claude-haiku-5-5", "anthropic/claude-haiku-5.5"]
input = 0.1
output = 0.5
cache_read = 0.01
cache_write = 0.125
cache_write_1h = 0.2

[[prices]]
models = [
    "claude-sonnet-4-6",
    "anthropic/claude-sonnet-4.6",
    "claude-sonnet-4-5",
    "anthropic/claude-sonnet-4.5",
]
input = 3
output = 15
cache_read = 0.3
cache_write = 3.75
cache_write_1h = 6

# Direct Gemini IDs use Google paid standard text rates, checked on 2026-10-21.
# https://ai.google.dev/gemini-api/docs/pricing
# The Argon promotion ends 2026-11-30. Its input, output, and cache-read rates then double.
# The Flash 3.6, 3.7, and 3.8 promotions end 2026-12-31. Their rates then double.
# Google bills cache storage by time, and this table excludes it.
# Separately counted cache writes, including one-hour writes, use the input rate.

[[prices]]
models = ["gemini-4-argon"]
input = 2
output = 10
cache_read = 0.1
cache_write = 2
cache_write_1h = 2

[[prices]]
models = ["gemini-3.8-flash", "gemini-3.7-flash", "gemini-3.6-flash"]
input = 0.75
output = 3.75
cache_read = 0.075
cache_write = 0.75
cache_write_1h = 0.75

[[prices]]
models = ["gemini-3.5-flash-lite"]
input = 0.3
output = 2.5
cache_read = 0.03
cache_write = 0.3
cache_write_1h = 0.3

# Direct DeepSeek IDs use peak rates, checked on 2026-10-21. Off-peak rates are half as much.
# https://api-docs.deepseek.com/quick_start/pricing/
# DeepSeek bills the older Flash IDs as deepseek-flash. This table uses one rate at all times.
# Separately counted cache writes, including one-hour writes, use the input rate.

[[prices]]
models = ["deepseek-flash", "deepseek-v4-flash", "deepseek-v4-flash-vision-exp"]
input = 0.3
output = 1.2
cache_read = 0.006
cache_write = 0.3
cache_write_1h = 0.3

[[prices]]
models = ["deepseek-v4-pro"]
input = 1.32
output = 3.96
cache_read = 0.044
cache_write = 1.32
cache_write_1h = 1.32

[[prices]]
models = ["openai/gpt-oss-120b"]
input = 0.15
output = 0.6
cache_read = 0.075
cache_write = 0.15

[[prices]]
models = ["openai/gpt-oss-20b"]
input = 0.018
output = 0.09
cache_read = 0.009
cache_write = 0.018

[[prices]]
models = ["google/gemini-4-argon"]
input = 2
output = 10
cache_read = 0.1
cache_write = 2

[[prices]]
models = ["google/gemini-3.8-flash"]
input = 0.825
output = 4.125
cache_read = 0.0825
cache_write = 0.825

[[prices]]
models = ["google/gemini-3.7-flash", "google/gemini-3.6-flash"]
input = 0.75
output = 3.75
cache_read = 0.075
cache_write = 0.75

[[prices]]
models = ["google/gemini-3.5-flash"]
input = 1.5
output = 9
cache_read = 0.15
cache_write = 1.5

[[prices]]
models = ["google/gemini-3.5-flash-lite", "google/gemini-2.5-flash"]
input = 0.3
output = 2.5
cache_read = 0.03
cache_write = 0.3

[[prices]]
models = ["google/gemini-3.1-flash-lite"]
input = 0.25
output = 1.5
cache_read = 0.025
cache_write = 0.25

[[prices]]
models = ["google/gemini-3.1-pro-preview"]
input = 2
output = 12
cache_read = 0.2
cache_write = 2

[[prices]]
models = ["google/gemini-2.5-pro"]
input = 1.25
output = 10
cache_read = 0.125
cache_write = 1.25

[[prices]]
models = ["google/gemini-2.5-flash-lite"]
input = 0.1
output = 0.4
cache_read = 0.01
cache_write = 0.1

[[prices]]
models = ["x-ai/grok-4.7", "x-ai/grok-4.6"]
input = 2
output = 6
cache_read = 0.5
cache_write = 2

[[prices]]
models = ["x-ai/grok-4.3"]
input = 1.25
output = 2.5
cache_read = 0.2
cache_write = 1.25

[[prices]]
models = ["moonshotai/kimi-k2.6"]
input = 0.65
output = 3.41
cache_read = 0.15
cache_write = 0.65

[[prices]]
models = ["moonshotai/kimi-k2.7-code"]
input = 0.6712
output = 3.35
cache_read = 0.18
cache_write = 0.6712

[[prices]]
models = ["z-ai/glm-5.1"]
input = 1.4
output = 4.4
cache_read = 0.26
cache_write = 1.4

[[prices]]
models = ["z-ai/glm-5.3-prime"]
input = 2.8
output = 8.8
cache_read = 0.56
cache_write = 2.8

[[prices]]
models = ["z-ai/glm-5.3-flashx"]
input = 0.37
output = 1.25
cache_read = 0.09
cache_write = 0.37

[[prices]]
models = ["qwen/qwen3.8-max-0902"]
input = 2
output = 6
cache_read = 0.25
cache_write = 2

[[prices]]
models = ["qwen/qwen3.8-flash"]
input = 0.15
output = 0.47
cache_read = 0.016
cache_write = 0.15

[[prices]]
models = ["qwen/qwen3.8-max-prime"]
input = 4
output = 12
cache_read = 0.5
cache_write = 4

[[prices]]
models = ["qwen/qwen3.7-plus"]
input = 0.32
output = 1.28
cache_read = 0.064
cache_write = 0.4

[[prices]]
models = ["qwen/qwen3.7-max"]
input = 1.475
output = 4.425
cache_read = 0.295
cache_write = 1.84375

[[prices]]
models = ["qwen/qwen3.7-flash"]
input = 0.03
output = 0.13
cache_read = 0.006
cache_write = 0.038

[[prices]]
models = ["minimax/minimax-m3", "minimax/minimax-m2.7"]
input = 0.3
output = 1.2
cache_read = 0.06
cache_write = 0.3

[[prices]]
models = ["nvidia/nemotron-3-ultra-550b-a55b"]
input = 0.6
output = 2.4
cache_read = 0.12
cache_write = 0.6

[[prices]]
models = ["nvidia/nemotron-3.5-super-vl"]
input = 0.15
output = 0.5
cache_read = 0.02
cache_write = 0.15

[[prices]]
models = ["nvidia/nemotron-3.5-lightning"]
input = 0.07
output = 0.2
cache_read = 0.04
cache_write = 0.07

[[prices]]
models = ["nvidia/nemotron-3-super-120b-a12b"]
input = 0.3
output = 2.4
cache_read = 0.15
cache_write = 0.3

[[prices]]
models = ["mistralai/mistral-large-4-0"]
input = 1.36
output = 4.18
cache_read = 0.14
cache_write = 1.36

[[prices]]
models = ["mistralai/mistral-medium-3-5"]
input = 1.5
output = 7.5
cache_read = 1.5
cache_write = 1.5

[[prices]]
models = ["mistralai/mistral-small-2603"]
input = 0.15
output = 0.6
cache_read = 0.015
cache_write = 0.15

[[prices]]
models = ["mistralai/devstral-2512"]
input = 0.4
output = 2
cache_read = 0.04
cache_write = 0.4

[[prices]]
models = [
    "meta/muse-spark-open",
    "meta/muse-spark-1.3",
    "meta/muse-spark-1.1",
    "meta/muse-spark-1.2",
]
input = 1.25
output = 4.25
cache_read = 0.15
cache_write = 1.25

[[prices]]
models = ["meta/muse-wonder"]
input = 4
output = 20
cache_read = 0.2
cache_write = 4

[[prices]]
models = ["stepfun/step-5-preview"]
input = 1
output = 2.7
cache_read = 0.1
cache_write = 1

[[prices]]
models = ["xiaomi/mimo-v2.6-pro"]
input = 0.435
output = 0.87
cache_read = 0.0036
cache_write = 0.435

[[prices]]
models = ["xiaomi/mimo-v2.6-flash"]
input = 0.14
output = 0.28
cache_read = 0.0028
cache_write = 0.14

# Only these explicit OpenRouter :free IDs use zero rates, checked on 2026-10-21.
# The same models without :free keep their paid rates.

[[prices]]
models = [
    "minimax/minimax-m3.1-flash:free",
    "nvidia/nemotron-3-ultra-550b-a55b:free",
    "nvidia/nemotron-3.5-super-vl:free",
    "nvidia/nemotron-3.5-lightning:free",
]
input = 0
output = 0
cache_read = 0
cache_write = 0

# These OpenRouter rates include provider discounts and can change with provider routing.
# OpenRouter's endpoint API lists provider offers for these GLM, Kimi, and DeepSeek rates.
# https://openrouter.ai/api/v1/models/{author}/{model}/endpoints
# DeepSeek 1017 and Hy4 use the advertised off-peak rates. Peak rates are higher.

[[prices]]
models = ["deepseek/deepseek-v4.1-flash"]
input = 0.02394
output = 0.375
cache_read = 0.000342
cache_write = 0.02394

[[prices]]
models = ["deepseek/deepseek-v4.1-flash-1017"]
input = 0.15
output = 0.6
cache_read = 0.003
cache_write = 0.15

[[prices]]
models = ["deepseek/deepseek-v4-flash-0731"]
input = 0.04444
output = 0.13332
cache_read = 0.001414
cache_write = 0.04444

[[prices]]
models = ["deepseek/deepseek-v4-pro-0813"]
input = 0.66
output = 1.98
cache_read = 0.022
cache_write = 0.66

[[prices]]
models = ["z-ai/glm-5.3"]
input = 0.079
output = 1.4
cache_read = 0.078
cache_write = 0.079

[[prices]]
models = ["z-ai/glm-5.3-flash"]
input = 0.02282
output = 0.05385
cache_read = 0.004885
cache_write = 0.02282

[[prices]]
models = ["z-ai/glm-5.2"]
input = 0.0341
output = 7
cache_read = 0.033
cache_write = 0.0341

[[prices]]
models = ["moonshotai/kimi-k3"]
input = 0.239
output = 11.936
cache_read = 0.21
cache_write = 0.239

[[prices]]
models = ["tencent/hy4-preview"]
input = 0.7506
output = 2.2509
cache_read = 0.0378
cache_write = 0.7506