Pricing
AgentBursar doesn't sell tokens. You bring your own OpenAI, Anthropic, Google, Groq or xAI keys, your providers bill you directly at their own prices, and AgentBursar puts per-agent caps, alerts and a kill switch in front of them.
Bring your own keys
during early access
- Your traffic uses only your own provider keys; your providers bill you directly
- No markup on tokens: we don't resell provider capacity
- Every control included: per-agent keys and caps, the kill switch, runaway-loop detection, run budgets and cap alerts
- Self-serve: add your provider keys, create and rotate agent keys, and set caps and alerts in your own dashboard
- Your provider account stays yours: its billing, rate limits and any dispute with the provider are between you and your provider
After early access
planned; prices not set yet
- We plan to charge a software subscription for the controls, never a fee on your tokens
- Existing customers get at least 30 days' notice before any paid plan applies to them
- Until then there is nothing to pay us, no balance to keep topped up and no card on file
Provider list prices, for reference
What the providers themselves charge, in US dollars per 1 million tokens. You pay these to your provider, not to us. AgentBursar meters each request at these list prices to enforce your caps and budgets, so the spend on your dashboard estimates your provider bill; your provider's own invoice is what counts (discounts, credits, batch pricing and taxes aren't reflected here). Prices are checked daily against public price databases (models.dev and LiteLLM) that track the providers' published prices. 65 models are listed today. With your own keys you can also use models that aren't listed; they are metered with an estimate.
OpenAI
| Model | Input | Output |
|---|---|---|
| gpt-4.1 | $2.00 | $8.00 |
| gpt-4.1-mini | $0.40 | $1.60 |
| gpt-4o | $2.50 | $10.00 |
| gpt-4o-2024-08-06 | $2.50 | $10.00 |
| gpt-4o-2024-11-20 | $2.50 | $10.00 |
| gpt-4o-mini | $0.15 | $0.60 |
| gpt-5 | $1.25 | $10.00 |
| gpt-5-mini | $0.25 | $2.00 |
| gpt-5-nano | $0.05 | $0.40 |
| gpt-5.1 | $1.25 | $10.00 |
| gpt-5.2 | $1.75 | $14.00 |
| gpt-5.4Above 272K input tokens: $5.00 / $22.50 | $2.50 | $15.00 |
| gpt-5.4-mini | $0.75 | $4.50 |
| gpt-5.4-nano | $0.20 | $1.25 |
| gpt-5.5Above 272K input tokens: $10.00 / $45.00 | $5.00 | $30.00 |
| gpt-5.6-lunaAbove 272K input tokens: $0.40 / $1.80 | $0.20 | $1.20 |
| gpt-5.6-solAbove 272K input tokens: $8.00 / $30.00 | $4.00 | $20.00 |
| gpt-5.6-terraAbove 272K input tokens: $4.00 / $18.00 | $2.00 | $12.00 |
| gpt-6-lunaAbove 272K input tokens: $0.20 / $0.75 | $0.10 | $0.50 |
| gpt-6-solAbove 272K input tokens: $4.00 / $15.00 | $2.00 | $10.00 |
| gpt-6.1-solAbove 272K input tokens: $4.00 / $15.00 | $2.00 | $10.00 |
| gpt-6.1-terraAbove 272K input tokens: $2.00 / $7.50 | $1.00 | $5.00 |
| o3 | $2.00 | $8.00 |
Anthropic
| Model | Input | Output |
|---|---|---|
| claude-haiku-4-5 | $1.00 | $5.00 |
| claude-haiku-4-5-20251001 | $1.00 | $5.00 |
| claude-haiku-5-5Above 100K input tokens: $0.50 / $2.50 | $0.10 | $0.50 |
| claude-opus-4-5 | $5.00 | $25.00 |
| claude-opus-4-5-20251101 | $5.00 | $25.00 |
| claude-opus-4-6 | $5.00 | $25.00 |
| claude-opus-4-7 | $5.00 | $25.00 |
| claude-opus-4-8 | $5.00 | $25.00 |
| claude-opus-5 | $5.00 | $25.00 |
| claude-opus-5-5 | $4.00 | $20.00 |
| claude-sonnet-4-5 | $3.00 | $15.00 |
| claude-sonnet-4-5-20250929 | $3.00 | $15.00 |
| claude-sonnet-4-6 | $3.00 | $15.00 |
| claude-sonnet-5 | $2.00 | $10.00 |
| claude-sonnet-5-5 | $2.00 | $10.00 |
| Model | Input | Output |
|---|---|---|
| gemini-2.5-flash | $0.30 | $2.50 |
| gemini-2.5-flash-lite | $0.10 | $0.40 |
| gemini-2.5-proAbove 200K input tokens: $2.50 / $15.00 | $1.25 | $10.00 |
| gemini-3-flash-preview | $0.50 | $3.00 |
| gemini-3.1-flash-lite | $0.25 | $1.50 |
| gemini-3.1-pro-previewAbove 200K input tokens: $4.00 / $18.00 | $2.00 | $12.00 |
| gemini-3.1-pro-preview-customtoolsAbove 200K input tokens: $4.00 / $18.00 | $2.00 | $12.00 |
| gemini-3.5-flash | $1.50 | $9.00 |
| gemini-3.5-flash-lite | $0.30 | $2.50 |
| gemini-3.6-flash | $0.75 | $3.75 |
| gemini-3.7-flash | $0.75 | $3.75 |
| gemini-3.8-flash | $0.75 | $3.75 |
| gemini-4-argon | $2.00 | $10.00 |
| gemini-flash-latest | $0.75 | $3.75 |
| gemini-flash-lite-latest | $0.30 | $2.50 |
| gemini-pro-latestAbove 200K input tokens: $4.00 / $18.00 | $2.00 | $12.00 |
Groq
| Model | Input | Output |
|---|---|---|
| openai/gpt-oss-120b | $0.15 | $0.60 |
| openai/gpt-oss-20b | $0.075 | $0.30 |
| qwen/qwen3.8-27b | $0.80 | $4.00 |
xAI
| Model | Input | Output |
|---|---|---|
| grok-3 | $1.25 | $2.50 |
| grok-4.20-0309-non-reasoningAbove 200K input tokens: $2.50 / $5.00 | $1.25 | $2.50 |
| grok-4.20-0309-reasoningAbove 200K input tokens: $2.50 / $5.00 | $1.25 | $2.50 |
| grok-4.3Above 200K input tokens: $2.50 / $5.00 | $1.25 | $2.50 |
| grok-4.5Above 200K input tokens: $4.00 / $12.00 | $2.00 | $6.00 |
| grok-4.6Above 200K input tokens: $4.00 / $12.00 | $2.00 | $6.00 |
| grok-4.7Above 200K input tokens: $4.00 / $12.00 | $2.00 | $6.00 |
| grok-build-0.1Above 200K input tokens: $2.00 / $4.00 | $1.00 | $2.00 |
Some models charge a higher rate for the whole request once its input exceeds a size threshold; those rates are shown under the model name. If a provider fails and a request is served by an equivalent model, it is metered at that model's price. You can turn that off per request. On the Anthropic Messages API (/v1/messages, used by Claude Code), prompt-cache writes and reads are metered at Anthropic's cache prices.