Overview
Model specifications
- Context
- 131,072 tokens
- Maximum output
- 32,768 tokens
- Architecture
- text->text
- Tokenizer
- GPT
- Knowledge cutoff
- 2024-06-30
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.018 per 1M tokens
- Output
- $0.09 per 1M tokens
API
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- medium
- Capabilities
- high, medium, low
API
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-20b","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
Reasoning
No · high · medium · low
API
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
12 providers
Checked: September 23, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Darkbloom
fp8- Context
- 131K
- Maximum output
- 33K
- Input
- $0.018
- Output
- $0.09
- Cache read
- Not provided
- Cache write
- Not provided
AkashML
fp4- Context
- 131K
- Maximum output
- 118K
- Input
- $0.02
- Output
- $0.1
- Cache read
- Not provided
- Cache write
- Not provided
DekaLLM
bf16- Context
- 131K
- Maximum output
- 118K
- Input
- $0.029
- Output
- $0.14
- Cache read
- Not provided
- Cache write
- Not provided
CoreWeave
fp4- Context
- 131K
- Maximum output
- 118K
- Input
- $0.03
- Output
- $0.13
- Cache read
- $0.03
- Cache write
- Not provided
DeepInfra
bf16- Context
- 131K
- Maximum output
- 118K
- Input
- $0.03
- Output
- $0.14
- Cache read
- Not provided
- Cache write
- Not provided
Parasail
fp4- Context
- 131K
- Maximum output
- 118K
- Input
- $0.03
- Output
- $0.15
- Cache read
- $0.02
- Cache write
- Not provided
Novita
fp4- Context
- 131K
- Maximum output
- 33K
- Input
- $0.04
- Output
- $0.15
- Cache read
- Not provided
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 131K
- Maximum output
- 8K
- Input
- $0.04
- Output
- $0.18
- Cache read
- Not provided
- Cache write
- Not provided
Amazon Bedrock
Not provided- Context
- 131K
- Maximum output
- 118K
- Input
- $0.07
- Output
- $0.15
- Cache read
- Not provided
- Cache write
- Not provided
Amazon Bedrock
Not provided- Context
- 131K
- Maximum output
- 118K
- Input
- $0.07
- Output
- $0.15
- Cache read
- Not provided
- Cache write
- Not provided
- Context
- 131K
- Maximum output
- 33K
- Input
- $0.07
- Output
- $0.25
- Cache read
- Not provided
- Cache write
- Not provided
Groq
Not provided- Context
- 131K
- Maximum output
- 66K
- Input
- $0.075
- Output
- $0.3
- Cache read
- $0.0375
- Cache write
- Not provided