Migrating from open-mistral-7b to open-mistral-nemo-2407
What changes when you move from open-mistral-7b to open-mistral-nemo-2407: context window 32,000 → 128,000 tokens.
- From
- open-mistral-7b
- Status
- Retired
- Shutdown
- Mar 30, 2025
- Time left
- —
- Status
- Retired
- Shutdown
- Jul 31, 2026
- Time left
- —
open-mistral-nemo-2407 is itself retired. Its replacement is ministral-8b-2512.
Prices
USD per 1M tokens, standard tier| Type | open-mistral-7b | open-mistral-nemo-2407 | Change |
|---|---|---|---|
| Input | Not published | $0.15first seen October 5, 2026 · source | — |
| Output | Not published | $0.15first seen October 5, 2026 · source | — |
Other tiers, prompt-size bands and modalities are on each model's page.
Limits
Tokens| Limit | open-mistral-7b | open-mistral-nemo-2407 | Change |
|---|---|---|---|
| Context window | 32,000 tokensin place when tracking began (October 6, 2026) · source | 128,000 tokensin place when tracking began (October 6, 2026) · source | +300% |
| Max output tokens | Not published | Not published | — |
Benchmarks
Same benchmark, source and setting on both sides| Benchmark | open-mistral-7b | open-mistral-nemo-2407 | Change |
|---|---|---|---|
| GPQA DiamondEpoch AI. | 13.2% | 29.9% | +16.7 pts |
| MATH Level 5Epoch AI. | 3.7% | 10.8% | +7.1 pts |
A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.
Features and parameters
Compare modelsNo feature is published for both models, so none can be compared.
Not published for open-mistral-7b: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.
Not published for open-mistral-nemo-2407: Prompt caching, Image input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.
Aliases
All aliasesNo aliases point at either model.
Checklist
- Change the model string from
open-mistral-7btoopen-mistral-nemo-2407.
Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: open-mistral-7b, open-mistral-nemo-2407.