Gemini 3.7 Flash
Gemini 3.7 Flash is deprecated: Google states that requests using its old API name now run on Gemini 3.8 Flash, so the name no longer guarantees the original model.
View model details →View sample outputs →Model comparisons
Gemini 3.7 Flash vs GPT 6.1 Terra
Gemini 3.7 Flash bills 32% less than GPT 6.1 Terra per million output tokens. Tier prices, request fields and limits side by side.
GPT 6.1 Terra
GPT 6.1 Terra reads screenshots and documents, then turns the supplied evidence into concise drafts or extracted fields. Terra defaults to a 4,096-token reply cap and permits 128,000; reserve part of that allowance for reasoning whenever effort is above none.
View model details →View sample outputs →Compare
The short answer
Start with the input you have, the result you want and your budget. These are the differences that affect that choice.
- Gemini 3.7 Flash costs 32% less per million output tokens. Compare the input and cache rates below for longer conversations.
Compare the published examples, then try the same input on both models with matching settings.
Test scores side by side
The Spicy Index and Freedom Score for both models, from the same daily calculation as the leaderboards.
| Measure | Gemini 3.7 Flash | GPT 6.1 Terra |
|---|---|---|
| Spicy Index | 77.8 | 79.9 |
| Freedom Score | 73.3 | Not yet tested |
| Evidence | Tested 5 of 5 probe types · 24 runs | — |
| Range if the rest pass | 73.3–73.3 | — |
| Price | $1.35 per 1M mixed tokens (3 input : 1 output) | $2.00 per 1M mixed tokens (3 input : 1 output) |
| Reviews | Read the Gemini 3.7 Flash review | Read the GPT 6.1 Terra review |
Preliminary · freedom evidence pending
See both on the leaderboard →Current price
Price at the same setting
A start price answers a different question than the one you have. These are the tiers both models publish, matched setting for setting, in US dollars per billed unit with no conversion step in between.
Swipe horizontally to compare all fields.
| Tier | Gemini 3.7 Flash | GPT 6.1 Terra | Difference |
|---|---|---|---|
| Input | $0.675 / 1 million tokens | $1 / 1 million tokens | Gemini 3.7 Flash −32% |
| Cached input | $0.068 / 1 million tokens | $0.05 / 1 million tokens | GPT 6.1 Terra −25% |
| Output | $3.38 / 1 million tokens | $5 / 1 million tokens | Gemini 3.7 Flash −32% |
What one ordinary job costs
- Gemini 3.7 Flash: $1.35 for one million input and two hundred thousand output tokens.
- GPT 6.1 Terra: $2 for one million input and two hundred thousand output tokens.
Arithmetic on the published rates at each model's own default setting, not a quote. The console prices your actual settings before a request is accepted.
About this comparison
Controls and limits
Every row here is read from the JSON Schema the endpoint validates against, so it matches what the API will really accept rather than a feature list written by hand.
Swipe horizontally to compare all fields.
| Controls and limits | Gemini 3.7 Flash | GPT 6.1 Terra |
|---|---|---|
| Supported tasks | chat | chat |
| Seed | Yes | No |
| Input context | 1,048,576 tokens | 1,050,000 tokens |
| Maximum output | 65,536 tokens | 128,000 tokens |
| Tool calling | Yes | Yes |
| Execution | Synchronous, with streaming | Synchronous, with streaming |
| Request timeout | 60 minutes | 10 minutes |
| Availability | Live | Live |
Do low-filter models allow every request?
Content policy, side by side
Two separate facts sit behind these labels. The first is what we do, which is nothing: no platform content filter, and no maturity flag to set on a request. The second is what each model does on its own, and that is the only part that varies between these two.
Gemini 3.7 Flash
Light
We add no content filter, but this model goes past its own limits only some of the time, even with a fiction-writing system prompt. Expect refusals and plan for retries. Legal and consent duties remain with the customer.
Usage note Gemini 3.7 Flash remains subject to its own content rules even though SpicyAPI adds no filter; use authorized material and respect privacy, consent and applicable terms. Use Gemini 3.7 Flash only with lawful, consensual adult material; content involving minors is prohibited.
Use these content labels to shortlist models, then open each model page for available examples and content-test details.
The label never changes your obligations. Age, consent, real-person likeness and the law where you operate stay with you, and SpicyAPI does not inspect each request.
Can I swap the model ID without changing the request body?
Request body, field by field
The task lifecycle is shared; the body is not. Each endpoint publishes its own JSON Schema and the API validates against that, so this is the list to reconcile before a switch.
- 9 fields appear in both request bodies under the same names. stop, tools, top_p, messages, max_tokens, temperature, tool_choice, response_format, reasoning_effort
- Only Gemini 3.7 Flash accepts: seed.
- Only GPT 6.1 Terra accepts: parallel_tool_calls.
- Gemini 3.7 Flash requires messages.
- GPT 6.1 Terra requires messages.
- Both reject unknown fields outright, so a parameter left over from the other model comes back as a validation error instead of being quietly ignored.
How to choose
How to choose
Maximum output
GPT 6.1 Terra can return more in one reply: up to 128,000 tokens against the other model's ceiling.
Input context
GPT 6.1 Terra takes the longer prompt: up to 1,050,000 input tokens in a single request.
Compare
Moving from one to the other
The model identifiers are google/gemini-3.7-flash/chat and openai/gpt-6.1-terra/chat, and both go in the same field of the same request.
Both return the response on the chat request. With streaming enabled, read the stream until it finishes; there is no media task to poll.
Both use the same submit-and-track flow, but their required inputs may differ. Check each model page before switching.
One key, one balance, one set of spend caps. Both bill to the same account in US dollars, and the per-key daily, monthly and lifetime limits apply to whichever one you call.
Questions developers ask
Which is cheaper, Gemini 3.7 Flash or GPT 6.1 Terra?
Which is cheaper, Gemini 3.7 Flash or GPT 6.1 Terra?
Gemini 3.7 Flash costs 32% less per million output tokens. Compare the input and cache rates below for longer conversations. Prices may change; check the estimate shown for your actual settings before submitting.
How long can a single request run?
Gemini 3.7 Flash allows 60 minutes per task and GPT 6.1 Terra allows 10. Those are ceilings rather than typical times — most requests finish far sooner — but they are what your own client timeout has to survive.
Prices and capabilities shown here come from the current public model catalogue. Check each model page for its latest inputs and examples.