89 lines
2.1 KiB
YAML
89 lines
2.1 KiB
YAML
providers:
|
|
llm-public:
|
|
baseUrl: https://example.com/v1
|
|
api: openai-completions
|
|
apiKey: LLM_PUBLIC_KEY
|
|
models:
|
|
- id: kimi-k2.6
|
|
name: KIMI K2.6
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
contextWindow: 262144
|
|
maxTokens: 262144
|
|
cost:
|
|
input: 0.95
|
|
output: 4
|
|
cacheRead: 0.16
|
|
cacheWrite: 0
|
|
- id: gpt-5.5
|
|
name: GPT-5.5
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
# models.dev also lists PDF input; OMP models.yml currently supports text/image only.
|
|
# models.dev limit.input: 920000
|
|
contextWindow: 1050000
|
|
maxTokens: 130000
|
|
cost:
|
|
input: 5
|
|
output: 30
|
|
cacheRead: 0.5
|
|
cacheWrite: 0
|
|
- id: gpt-5.3-codex-spark
|
|
name: GPT-5.3 Codex Spark
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
contextWindow: 400000
|
|
maxTokens: 128000
|
|
cost:
|
|
input: 0
|
|
output: 0
|
|
cacheRead: 0
|
|
cacheWrite: 0
|
|
- id: gpt-5.4
|
|
name: GPT-5.4
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
# prompts with >272K input tokens are priced at 2x input and 1.5x output for the full session for standard, batch, and flex.
|
|
contextWindow: 272000
|
|
maxTokens: 128000
|
|
cost:
|
|
input: 2.5
|
|
output: 15
|
|
cacheRead: 0.25
|
|
cacheWrite: 0
|
|
- id: gpt-5.4-mini
|
|
name: GPT-5.4 mini
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
contextWindow: 400000
|
|
maxTokens: 128000
|
|
cost:
|
|
input: 0.75
|
|
output: 4.5
|
|
cacheRead: 0.075
|
|
cacheWrite: 0
|
|
- id: gpt-5.3-codex
|
|
name: GPT-5.3 Codex
|
|
reasoning: true
|
|
input:
|
|
- text
|
|
- image
|
|
contextWindow: 400000
|
|
maxTokens: 128000
|
|
cost:
|
|
input: 0
|
|
output: 0
|
|
cacheRead: 0
|
|
cacheWrite: 0
|
|
|