Coding API
Specialized AI models for coding tasks. Requesty routes to 24 Coding API models starting at $0.30 per 1M input tokens with context windows up to 1.0M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
claude-sonnet-4-20250514MMLU Pro
81.2%
GPQA
70.1%
HumanEval
89.8%
SWE-Bench
65.2%
All Coding API models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
claude-opus-4-20250514 | 200K | 32K | $15.00 | $75.00 | 👁🧠🔧⚡🖥 | — |
claude-sonnet-4-20250514 | 200K | 64K | $3.00 | $15.00 | 👁🧠🔧⚡🖥 | 65% |
gemini-2.5-flash @us-east1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @us-east5 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @us-south1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @us-west1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @europe-west4 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @europe-west8 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @us-central1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @europe-central2 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @europe-north1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-flash @europe-west1 | 1.0M | 66K | $0.30 | $2.50 | 👁🧠🔧⚡ | 53% |
gemini-2.5-pro @us-south1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @europe-west1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @europe-west8 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @europe-west4 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @us-central1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @us-east1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @us-east5 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @us-west1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @europe-central2 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
gemini-2.5-pro @europe-north1 | 1.0M | 66K | $1.25 | $10.00 | 👁🧠🔧⚡🖥 | 64% |
About Coding API on Requesty
How many Coding API models are available through Requesty?
Requesty routes to 24 Coding API models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Coding API model?
The cheapest Coding API model starts at $0.30 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Coding API pricing?
No. Requesty passes through exactly what Coding API charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Coding API models?
Coding API's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Coding API models hosted?
Coding API models are hosted in 🌍 Global. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Coding API rows in the models explorer.