Models & Pricing

GPT-6.1 Terra vs GPT-6.1 Sol

Choose two or three models. Copy the URL to share your selection.

ComparisonGPT-6.1 Terra
gpt-6.1-terra
GPT-6.1 Sol
gpt-6.1-sol
TypeChatChat
Best forVisual reasoning, document analysis and clear writingNear-flagship agentic coding and computer use at a lower price
TokenRex price$0.70 in / $3.50 out per 1M tokens$1.40 in / $7.00 out per 1M tokens
Cached input / 1M tokens$0.035 per 1M tokens$0.07 per 1M tokens
Cache write / 1M tokens$0.875 per 1M tokens$1.75 per 1M tokens
Cached outputNot offered · standard output rate appliesNot offered · standard output rate applies
Web search$7.00 per 1K searches$7.00 per 1K searches
Market price$1.00 in / $5.00 out per 1M tokens$2.00 in / $10.00 out per 1M tokens
Context window (provider)1,050,000 tokens1,050,000 tokens
Input token limit (provider)Within the context windowWithin the context window
Maximum output128,000 tokens128,000 tokens
Knowledge cutoffJune 1, 2026April 2026
Vendor input modalitiesText, ImageText, Image
Vendor output modalitiesTextText
TokenRex endpointsPOST /v1/chat/completions · POST /v1/responsesPOST /v1/chat/completions · POST /v1/responses
TokenRex inputText, Image—
TokenRex outputText—
ThinkingLow, Medium, High, Extra high and Max; Max requires Responses. Native none is also accepted.—
ResponsesStreaming, function tools, strict JSON and built-in web search verified with direct requests.—
FastPriority serving verified as service_tier fast; 2× standard token rates. Bill the tier actually served.—
Benchmarks
Benchmark evidence—5 source-linked results
DeepSWE v1.1—
75.2%

Self-reported by OpenAI in the GPT-6.1 Sol launch post (best of five reasoning efforts), September 2026.

OpenAI · Introducing GPT-6.1 Sol
Terminal-Bench Science 0.1—
57%

Self-reported by OpenAI in the GPT-6.1 Sol launch post (max reasoning effort), September 2026.

OpenAI · Introducing GPT-6.1 Sol
OSWorld 2.0—
71.4%

Self-reported by OpenAI in the GPT-6.1 Sol launch post (offline set, partial credit, best of five efforts), September 2026.

OpenAI · Introducing GPT-6.1 Sol
AutomationBench 1.0.6—
36.1%

Self-reported by OpenAI in the GPT-6.1 Sol launch post (best of five efforts), September 2026.

OpenAI · Introducing GPT-6.1 Sol
GDP.pdf—
32%

Self-reported by OpenAI in the GPT-6.1 Sol launch post (best of five efforts), September 2026.

OpenAI · Introducing GPT-6.1 Sol

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

GPT-6.1 Terra

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (5)
  • Official Standard rates per 1M tokens: $1 input, $5 output, $0.05 cached input, $1.25 cache write (30 minutes); current TokenRex offer applies to these rates.
  • Above 272,000 input tokens, the entire request uses 2× input/cache rates and 1.5× output rates. Fast adds its 2× token multiplier.
  • 12-hour cache writes cost $2.50 per 1M tokens before offer and long-context multipliers; use prompt_cache_options.ttl=12h on Responses. Cached output is not offered.
  • Official launch material mentions benchmark comparisons, but no exact-version numeric scores were verified during this review. Benchmark gaps are left empty; no other model scores are inherited.
  • Maximum-capacity inputs and outputs, repeated cache hits and hosted computer-use execution were not independently tested.

GPT-6.1 Sol

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (2)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex.
  • All benchmark scores are self-reported by OpenAI at launch (29 September 2026); TokenRex has not re-run them.

Popular comparisons

Open the cost calculator →