Overview
Model specifications
- Context
- 1,048,576 tokens
- Maximum output
- 512,000 tokens
- Architecture
- text+image+video->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.3 per 1M tokens
- Output
- $1.2 per 1M tokens
- Cache read
- $0.06 per 1M tokens
API
Model configuration
Default parameters
temperature- 1
top_p- 0.95
Reasoning
- Reasoning required
- No
- Default parameters
- No
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":"minimax/minimax-m3","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
textimagevideo
Output
text
Reasoning
No
API
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
12 providers
Checked: September 7, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
CoreWeave
fp4- Context
- 262K
- Maximum output
- 236K
- Input
- $0.23
- Output
- $0.96
- Cache read
- $0.05
- Cache write
- Not provided
GMICloud
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.24
- Output
- $0.96
- Cache read
- $0.048
- Cache write
- Not provided
DeepInfra
fp8- Context
- 524K
- Maximum output
- 512K
- Input
- $0.28
- Output
- $1.1
- Cache read
- $0.056
- Cache write
- Not provided
StreamLake
fp8- Context
- 1M
- Maximum output
- 512K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
Venice
fp8- Context
- 524K
- Maximum output
- 66K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
Together
Not provided- Context
- 524K
- Maximum output
- 472K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
Parasail
fp8- Context
- 1.0M
- Maximum output
- 524K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
AtlasCloud
fp8- Context
- 524K
- Maximum output
- 524K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
Novita
fp8- Context
- 1M
- Maximum output
- 131K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
Minimax
fp8- Context
- 524K
- Maximum output
- 512K
- Input
- $0.3
- Output
- $1.2
- Cache read
- $0.06
- Cache write
- Not provided
SambaNova
Not provided- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.6
- Output
- $2.4
- Cache read
- Not provided
- Cache write
- Not provided
ModelRun
fp4- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.75
- Output
- $3
- Cache read
- $0.15
- Cache write
- Not provided